Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-100/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-100/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "tlrm/Q25-1.5B-UC",
+  "architectures": [
+    "Qwen2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-100/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b87410c50023b1ddbdcbb2daa5546face77bc435e00c2871dce5de23a9937364
+size 4996670464

checkpoint-100/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3911f8f7f65ffaf10a6e7e3f4abd5c9cf8504a01c290ac2da58ef98869a93c3
+size 1178231192

checkpoint-100/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 6174863360
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "score.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-100/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-100/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n   {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,1933 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.25,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "Batch Sum": 52.814453125,
+      "accuracy": 0.546875,
+      "epoch": 0,
+      "step": 0
+    },
+    {
+      "Batch Sum": 52.524169921875,
+      "accuracy": 0.40625,
+      "epoch": 0,
+      "step": 0
+    },
+    {
+      "epoch": 0.0025,
+      "grad_norm": 12.003690719604492,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 0.714,
+      "step": 1
+    },
+    {
+      "Batch Sum": 52.9404296875,
+      "accuracy": 0.515625,
+      "epoch": 0.0025,
+      "step": 1
+    },
+    {
+      "Batch Sum": 48.3984375,
+      "accuracy": 0.625,
+      "epoch": 0.0025,
+      "step": 1
+    },
+    {
+      "epoch": 0.005,
+      "grad_norm": 14.317296981811523,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 0.6849,
+      "step": 2
+    },
+    {
+      "Batch Sum": 52.79443359375,
+      "accuracy": 0.484375,
+      "epoch": 0.005,
+      "step": 2
+    },
+    {
+      "Batch Sum": 53.980224609375,
+      "accuracy": 0.578125,
+      "epoch": 0.005,
+      "step": 2
+    },
+    {
+      "epoch": 0.0075,
+      "grad_norm": 21.00113296508789,
+      "learning_rate": 7.5e-07,
+      "loss": 0.7106,
+      "step": 3
+    },
+    {
+      "Batch Sum": 53.60833740234375,
+      "accuracy": 0.453125,
+      "epoch": 0.0075,
+      "step": 3
+    },
+    {
+      "Batch Sum": 52.896728515625,
+      "accuracy": 0.578125,
+      "epoch": 0.0075,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 13.431326866149902,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.6978,
+      "step": 4
+    },
+    {
+      "Batch Sum": 54.1025390625,
+      "accuracy": 0.65625,
+      "epoch": 0.01,
+      "step": 4
+    },
+    {
+      "Batch Sum": 54.279052734375,
+      "accuracy": 0.53125,
+      "epoch": 0.01,
+      "step": 4
+    },
+    {
+      "epoch": 0.0125,
+      "grad_norm": 13.951983451843262,
+      "learning_rate": 1.25e-06,
+      "loss": 0.6883,
+      "step": 5
+    },
+    {
+      "Batch Sum": 53.18408203125,
+      "accuracy": 0.578125,
+      "epoch": 0.0125,
+      "step": 5
+    },
+    {
+      "Batch Sum": 49.6630859375,
+      "accuracy": 0.53125,
+      "epoch": 0.0125,
+      "step": 5
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 11.490130424499512,
+      "learning_rate": 1.5e-06,
+      "loss": 0.6818,
+      "step": 6
+    },
+    {
+      "Batch Sum": 54.36865234375,
+      "accuracy": 0.546875,
+      "epoch": 0.015,
+      "step": 6
+    },
+    {
+      "Batch Sum": 53.27685546875,
+      "accuracy": 0.515625,
+      "epoch": 0.015,
+      "step": 6
+    },
+    {
+      "epoch": 0.0175,
+      "grad_norm": 18.882749557495117,
+      "learning_rate": 1.75e-06,
+      "loss": 0.7198,
+      "step": 7
+    },
+    {
+      "Batch Sum": 58.3974609375,
+      "accuracy": 0.421875,
+      "epoch": 0.0175,
+      "step": 7
+    },
+    {
+      "Batch Sum": 56.97265625,
+      "accuracy": 0.6875,
+      "epoch": 0.0175,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 12.89813232421875,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.6877,
+      "step": 8
+    },
+    {
+      "Batch Sum": 56.07861328125,
+      "accuracy": 0.625,
+      "epoch": 0.02,
+      "step": 8
+    },
+    {
+      "Batch Sum": 57.08154296875,
+      "accuracy": 0.609375,
+      "epoch": 0.02,
+      "step": 8
+    },
+    {
+      "epoch": 0.0225,
+      "grad_norm": 16.434814453125,
+      "learning_rate": 2.25e-06,
+      "loss": 0.6739,
+      "step": 9
+    },
+    {
+      "Batch Sum": 59.09326171875,
+      "accuracy": 0.453125,
+      "epoch": 0.0225,
+      "step": 9
+    },
+    {
+      "Batch Sum": 61.3369140625,
+      "accuracy": 0.546875,
+      "epoch": 0.0225,
+      "step": 9
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 13.62090015411377,
+      "learning_rate": 2.5e-06,
+      "loss": 0.6856,
+      "step": 10
+    },
+    {
+      "Batch Sum": 70.0703125,
+      "accuracy": 0.609375,
+      "epoch": 0.025,
+      "step": 10
+    },
+    {
+      "Batch Sum": 64.751953125,
+      "accuracy": 0.578125,
+      "epoch": 0.025,
+      "step": 10
+    },
+    {
+      "epoch": 0.0275,
+      "grad_norm": 13.072342872619629,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.6546,
+      "step": 11
+    },
+    {
+      "Batch Sum": 73.357421875,
+      "accuracy": 0.609375,
+      "epoch": 0.0275,
+      "step": 11
+    },
+    {
+      "Batch Sum": 72.185546875,
+      "accuracy": 0.578125,
+      "epoch": 0.0275,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 13.209249496459961,
+      "learning_rate": 3e-06,
+      "loss": 0.6519,
+      "step": 12
+    },
+    {
+      "Batch Sum": 77.0615234375,
+      "accuracy": 0.703125,
+      "epoch": 0.03,
+      "step": 12
+    },
+    {
+      "Batch Sum": 78.0577392578125,
+      "accuracy": 0.703125,
+      "epoch": 0.03,
+      "step": 12
+    },
+    {
+      "epoch": 0.0325,
+      "grad_norm": 12.592546463012695,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.6092,
+      "step": 13
+    },
+    {
+      "Batch Sum": 91.876953125,
+      "accuracy": 0.625,
+      "epoch": 0.0325,
+      "step": 13
+    },
+    {
+      "Batch Sum": 87.7666015625,
+      "accuracy": 0.6875,
+      "epoch": 0.0325,
+      "step": 13
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 14.43427848815918,
+      "learning_rate": 3.5e-06,
+      "loss": 0.601,
+      "step": 14
+    },
+    {
+      "Batch Sum": 97.5859375,
+      "accuracy": 0.65625,
+      "epoch": 0.035,
+      "step": 14
+    },
+    {
+      "Batch Sum": 107.59765625,
+      "accuracy": 0.71875,
+      "epoch": 0.035,
+      "step": 14
+    },
+    {
+      "epoch": 0.0375,
+      "grad_norm": 12.276965141296387,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.6045,
+      "step": 15
+    },
+    {
+      "Batch Sum": 111.8828125,
+      "accuracy": 0.59375,
+      "epoch": 0.0375,
+      "step": 15
+    },
+    {
+      "Batch Sum": 116.759765625,
+      "accuracy": 0.6875,
+      "epoch": 0.0375,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 12.269201278686523,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.6262,
+      "step": 16
+    },
+    {
+      "Batch Sum": 120.9140625,
+      "accuracy": 0.625,
+      "epoch": 0.04,
+      "step": 16
+    },
+    {
+      "Batch Sum": 125.150390625,
+      "accuracy": 0.703125,
+      "epoch": 0.04,
+      "step": 16
+    },
+    {
+      "epoch": 0.0425,
+      "grad_norm": 12.212128639221191,
+      "learning_rate": 4.25e-06,
+      "loss": 0.6265,
+      "step": 17
+    },
+    {
+      "Batch Sum": 136.623046875,
+      "accuracy": 0.71875,
+      "epoch": 0.0425,
+      "step": 17
+    },
+    {
+      "Batch Sum": 133.275390625,
+      "accuracy": 0.640625,
+      "epoch": 0.0425,
+      "step": 17
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 17.11771583557129,
+      "learning_rate": 4.5e-06,
+      "loss": 0.596,
+      "step": 18
+    },
+    {
+      "Batch Sum": 155.64453125,
+      "accuracy": 0.71875,
+      "epoch": 0.045,
+      "step": 18
+    },
+    {
+      "Batch Sum": 152.97265625,
+      "accuracy": 0.671875,
+      "epoch": 0.045,
+      "step": 18
+    },
+    {
+      "epoch": 0.0475,
+      "grad_norm": 17.395545959472656,
+      "learning_rate": 4.75e-06,
+      "loss": 0.6295,
+      "step": 19
+    },
+    {
+      "Batch Sum": 173.0703125,
+      "accuracy": 0.65625,
+      "epoch": 0.0475,
+      "step": 19
+    },
+    {
+      "Batch Sum": 173.05078125,
+      "accuracy": 0.671875,
+      "epoch": 0.0475,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 24.041831970214844,
+      "learning_rate": 5e-06,
+      "loss": 0.6095,
+      "step": 20
+    },
+    {
+      "Batch Sum": 191.30859375,
+      "accuracy": 0.765625,
+      "epoch": 0.05,
+      "step": 20
+    },
+    {
+      "Batch Sum": 196.74609375,
+      "accuracy": 0.6875,
+      "epoch": 0.05,
+      "step": 20
+    },
+    {
+      "epoch": 0.0525,
+      "grad_norm": 13.471965789794922,
+      "learning_rate": 4.986842105263158e-06,
+      "loss": 0.527,
+      "step": 21
+    },
+    {
+      "Batch Sum": 205.40625,
+      "accuracy": 0.703125,
+      "epoch": 0.0525,
+      "step": 21
+    },
+    {
+      "Batch Sum": 204.26953125,
+      "accuracy": 0.703125,
+      "epoch": 0.0525,
+      "step": 21
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 22.169654846191406,
+      "learning_rate": 4.973684210526316e-06,
+      "loss": 0.6532,
+      "step": 22
+    },
+    {
+      "Batch Sum": 208.29296875,
+      "accuracy": 0.578125,
+      "epoch": 0.055,
+      "step": 22
+    },
+    {
+      "Batch Sum": 208.50390625,
+      "accuracy": 0.75,
+      "epoch": 0.055,
+      "step": 22
+    },
+    {
+      "epoch": 0.0575,
+      "grad_norm": 21.459922790527344,
+      "learning_rate": 4.960526315789474e-06,
+      "loss": 0.6456,
+      "step": 23
+    },
+    {
+      "Batch Sum": 207.7421875,
+      "accuracy": 0.78125,
+      "epoch": 0.0575,
+      "step": 23
+    },
+    {
+      "Batch Sum": 205.7421875,
+      "accuracy": 0.625,
+      "epoch": 0.0575,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 12.531883239746094,
+      "learning_rate": 4.947368421052632e-06,
+      "loss": 0.5219,
+      "step": 24
+    },
+    {
+      "Batch Sum": 211.6640625,
+      "accuracy": 0.71875,
+      "epoch": 0.06,
+      "step": 24
+    },
+    {
+      "Batch Sum": 208.45703125,
+      "accuracy": 0.703125,
+      "epoch": 0.06,
+      "step": 24
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 16.02347755432129,
+      "learning_rate": 4.9342105263157895e-06,
+      "loss": 0.5895,
+      "step": 25
+    },
+    {
+      "Batch Sum": 213.375,
+      "accuracy": 0.640625,
+      "epoch": 0.0625,
+      "step": 25
+    },
+    {
+      "Batch Sum": 203.58203125,
+      "accuracy": 0.703125,
+      "epoch": 0.0625,
+      "step": 25
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 12.315845489501953,
+      "learning_rate": 4.921052631578948e-06,
+      "loss": 0.5732,
+      "step": 26
+    },
+    {
+      "Batch Sum": 202.23828125,
+      "accuracy": 0.734375,
+      "epoch": 0.065,
+      "step": 26
+    },
+    {
+      "Batch Sum": 197.6953125,
+      "accuracy": 0.703125,
+      "epoch": 0.065,
+      "step": 26
+    },
+    {
+      "epoch": 0.0675,
+      "grad_norm": 10.496895790100098,
+      "learning_rate": 4.907894736842106e-06,
+      "loss": 0.5467,
+      "step": 27
+    },
+    {
+      "Batch Sum": 183.37890625,
+      "accuracy": 0.703125,
+      "epoch": 0.0675,
+      "step": 27
+    },
+    {
+      "Batch Sum": 185.86328125,
+      "accuracy": 0.75,
+      "epoch": 0.0675,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 10.82455825805664,
+      "learning_rate": 4.894736842105264e-06,
+      "loss": 0.5028,
+      "step": 28
+    },
+    {
+      "Batch Sum": 179.2158203125,
+      "accuracy": 0.71875,
+      "epoch": 0.07,
+      "step": 28
+    },
+    {
+      "Batch Sum": 179.328125,
+      "accuracy": 0.734375,
+      "epoch": 0.07,
+      "step": 28
+    },
+    {
+      "epoch": 0.0725,
+      "grad_norm": 13.485640525817871,
+      "learning_rate": 4.881578947368422e-06,
+      "loss": 0.5516,
+      "step": 29
+    },
+    {
+      "Batch Sum": 174.9296875,
+      "accuracy": 0.703125,
+      "epoch": 0.0725,
+      "step": 29
+    },
+    {
+      "Batch Sum": 172.44921875,
+      "accuracy": 0.734375,
+      "epoch": 0.0725,
+      "step": 29
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 11.573375701904297,
+      "learning_rate": 4.8684210526315795e-06,
+      "loss": 0.5523,
+      "step": 30
+    },
+    {
+      "Batch Sum": 170.3046875,
+      "accuracy": 0.671875,
+      "epoch": 0.075,
+      "step": 30
+    },
+    {
+      "Batch Sum": 174.54296875,
+      "accuracy": 0.703125,
+      "epoch": 0.075,
+      "step": 30
+    },
+    {
+      "epoch": 0.0775,
+      "grad_norm": 10.271368026733398,
+      "learning_rate": 4.855263157894737e-06,
+      "loss": 0.5549,
+      "step": 31
+    },
+    {
+      "Batch Sum": 168.15625,
+      "accuracy": 0.75,
+      "epoch": 0.0775,
+      "step": 31
+    },
+    {
+      "Batch Sum": 169.49609375,
+      "accuracy": 0.671875,
+      "epoch": 0.0775,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 9.423661231994629,
+      "learning_rate": 4.842105263157895e-06,
+      "loss": 0.5279,
+      "step": 32
+    },
+    {
+      "Batch Sum": 166.53125,
+      "accuracy": 0.765625,
+      "epoch": 0.08,
+      "step": 32
+    },
+    {
+      "Batch Sum": 169.66015625,
+      "accuracy": 0.75,
+      "epoch": 0.08,
+      "step": 32
+    },
+    {
+      "epoch": 0.0825,
+      "grad_norm": 11.485343933105469,
+      "learning_rate": 4.828947368421053e-06,
+      "loss": 0.5109,
+      "step": 33
+    },
+    {
+      "Batch Sum": 169.38671875,
+      "accuracy": 0.6875,
+      "epoch": 0.0825,
+      "step": 33
+    },
+    {
+      "Batch Sum": 172.9375,
+      "accuracy": 0.796875,
+      "epoch": 0.0825,
+      "step": 33
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 10.612264633178711,
+      "learning_rate": 4.815789473684211e-06,
+      "loss": 0.555,
+      "step": 34
+    },
+    {
+      "Batch Sum": 179.78515625,
+      "accuracy": 0.71875,
+      "epoch": 0.085,
+      "step": 34
+    },
+    {
+      "Batch Sum": 173.041015625,
+      "accuracy": 0.75,
+      "epoch": 0.085,
+      "step": 34
+    },
+    {
+      "epoch": 0.0875,
+      "grad_norm": 9.249446868896484,
+      "learning_rate": 4.802631578947369e-06,
+      "loss": 0.528,
+      "step": 35
+    },
+    {
+      "Batch Sum": 169.671875,
+      "accuracy": 0.765625,
+      "epoch": 0.0875,
+      "step": 35
+    },
+    {
+      "Batch Sum": 184.578125,
+      "accuracy": 0.734375,
+      "epoch": 0.0875,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 8.817283630371094,
+      "learning_rate": 4.789473684210527e-06,
+      "loss": 0.452,
+      "step": 36
+    },
+    {
+      "Batch Sum": 182.33984375,
+      "accuracy": 0.765625,
+      "epoch": 0.09,
+      "step": 36
+    },
+    {
+      "Batch Sum": 190.103515625,
+      "accuracy": 0.75,
+      "epoch": 0.09,
+      "step": 36
+    },
+    {
+      "epoch": 0.0925,
+      "grad_norm": 18.01405906677246,
+      "learning_rate": 4.7763157894736844e-06,
+      "loss": 0.5748,
+      "step": 37
+    },
+    {
+      "Batch Sum": 192.9296875,
+      "accuracy": 0.796875,
+      "epoch": 0.0925,
+      "step": 37
+    },
+    {
+      "Batch Sum": 195.75390625,
+      "accuracy": 0.734375,
+      "epoch": 0.0925,
+      "step": 37
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 10.098393440246582,
+      "learning_rate": 4.763157894736842e-06,
+      "loss": 0.4995,
+      "step": 38
+    },
+    {
+      "Batch Sum": 199.21484375,
+      "accuracy": 0.75,
+      "epoch": 0.095,
+      "step": 38
+    },
+    {
+      "Batch Sum": 204.1640625,
+      "accuracy": 0.703125,
+      "epoch": 0.095,
+      "step": 38
+    },
+    {
+      "epoch": 0.0975,
+      "grad_norm": 13.419852256774902,
+      "learning_rate": 4.75e-06,
+      "loss": 0.5398,
+      "step": 39
+    },
+    {
+      "Batch Sum": 209.2578125,
+      "accuracy": 0.71875,
+      "epoch": 0.0975,
+      "step": 39
+    },
+    {
+      "Batch Sum": 213.6796875,
+      "accuracy": 0.640625,
+      "epoch": 0.0975,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 12.879420280456543,
+      "learning_rate": 4.736842105263158e-06,
+      "loss": 0.5389,
+      "step": 40
+    },
+    {
+      "Batch Sum": 220.0625,
+      "accuracy": 0.734375,
+      "epoch": 0.1,
+      "step": 40
+    },
+    {
+      "Batch Sum": 214.107421875,
+      "accuracy": 0.703125,
+      "epoch": 0.1,
+      "step": 40
+    },
+    {
+      "epoch": 0.1025,
+      "grad_norm": 10.593208312988281,
+      "learning_rate": 4.723684210526316e-06,
+      "loss": 0.4675,
+      "step": 41
+    },
+    {
+      "Batch Sum": 225.80078125,
+      "accuracy": 0.796875,
+      "epoch": 0.1025,
+      "step": 41
+    },
+    {
+      "Batch Sum": 218.39453125,
+      "accuracy": 0.765625,
+      "epoch": 0.1025,
+      "step": 41
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 10.301755905151367,
+      "learning_rate": 4.710526315789474e-06,
+      "loss": 0.4833,
+      "step": 42
+    },
+    {
+      "Batch Sum": 234.8203125,
+      "accuracy": 0.765625,
+      "epoch": 0.105,
+      "step": 42
+    },
+    {
+      "Batch Sum": 229.140625,
+      "accuracy": 0.734375,
+      "epoch": 0.105,
+      "step": 42
+    },
+    {
+      "epoch": 0.1075,
+      "grad_norm": 11.743901252746582,
+      "learning_rate": 4.697368421052632e-06,
+      "loss": 0.5026,
+      "step": 43
+    },
+    {
+      "Batch Sum": 226.81640625,
+      "accuracy": 0.734375,
+      "epoch": 0.1075,
+      "step": 43
+    },
+    {
+      "Batch Sum": 225.296875,
+      "accuracy": 0.75,
+      "epoch": 0.1075,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 13.593162536621094,
+      "learning_rate": 4.68421052631579e-06,
+      "loss": 0.5254,
+      "step": 44
+    },
+    {
+      "Batch Sum": 227.609375,
+      "accuracy": 0.703125,
+      "epoch": 0.11,
+      "step": 44
+    },
+    {
+      "Batch Sum": 216.0625,
+      "accuracy": 0.765625,
+      "epoch": 0.11,
+      "step": 44
+    },
+    {
+      "epoch": 0.1125,
+      "grad_norm": 11.014060974121094,
+      "learning_rate": 4.671052631578948e-06,
+      "loss": 0.4679,
+      "step": 45
+    },
+    {
+      "Batch Sum": 227.234375,
+      "accuracy": 0.640625,
+      "epoch": 0.1125,
+      "step": 45
+    },
+    {
+      "Batch Sum": 222.55078125,
+      "accuracy": 0.734375,
+      "epoch": 0.1125,
+      "step": 45
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 14.091309547424316,
+      "learning_rate": 4.657894736842106e-06,
+      "loss": 0.5738,
+      "step": 46
+    },
+    {
+      "Batch Sum": 217.4609375,
+      "accuracy": 0.6875,
+      "epoch": 0.115,
+      "step": 46
+    },
+    {
+      "Batch Sum": 224.85546875,
+      "accuracy": 0.671875,
+      "epoch": 0.115,
+      "step": 46
+    },
+    {
+      "epoch": 0.1175,
+      "grad_norm": 12.615903854370117,
+      "learning_rate": 4.6447368421052635e-06,
+      "loss": 0.5464,
+      "step": 47
+    },
+    {
+      "Batch Sum": 211.90625,
+      "accuracy": 0.75,
+      "epoch": 0.1175,
+      "step": 47
+    },
+    {
+      "Batch Sum": 207.115234375,
+      "accuracy": 0.734375,
+      "epoch": 0.1175,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 10.995285987854004,
+      "learning_rate": 4.631578947368421e-06,
+      "loss": 0.4911,
+      "step": 48
+    },
+    {
+      "Batch Sum": 198.1484375,
+      "accuracy": 0.734375,
+      "epoch": 0.12,
+      "step": 48
+    },
+    {
+      "Batch Sum": 195.65234375,
+      "accuracy": 0.765625,
+      "epoch": 0.12,
+      "step": 48
+    },
+    {
+      "epoch": 0.1225,
+      "grad_norm": 12.166397094726562,
+      "learning_rate": 4.618421052631579e-06,
+      "loss": 0.4656,
+      "step": 49
+    },
+    {
+      "Batch Sum": 192.26953125,
+      "accuracy": 0.703125,
+      "epoch": 0.1225,
+      "step": 49
+    },
+    {
+      "Batch Sum": 187.31640625,
+      "accuracy": 0.78125,
+      "epoch": 0.1225,
+      "step": 49
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 12.223002433776855,
+      "learning_rate": 4.605263157894737e-06,
+      "loss": 0.5363,
+      "step": 50
+    },
+    {
+      "Batch Sum": 192.75390625,
+      "accuracy": 0.796875,
+      "epoch": 0.125,
+      "step": 50
+    },
+    {
+      "Batch Sum": 182.095703125,
+      "accuracy": 0.734375,
+      "epoch": 0.125,
+      "step": 50
+    },
+    {
+      "epoch": 0.1275,
+      "grad_norm": 10.82153606414795,
+      "learning_rate": 4.592105263157895e-06,
+      "loss": 0.4713,
+      "step": 51
+    },
+    {
+      "Batch Sum": 187.1015625,
+      "accuracy": 0.71875,
+      "epoch": 0.1275,
+      "step": 51
+    },
+    {
+      "Batch Sum": 185.41796875,
+      "accuracy": 0.703125,
+      "epoch": 0.1275,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 13.1001558303833,
+      "learning_rate": 4.578947368421053e-06,
+      "loss": 0.5496,
+      "step": 52
+    },
+    {
+      "Batch Sum": 199.91015625,
+      "accuracy": 0.765625,
+      "epoch": 0.13,
+      "step": 52
+    },
+    {
+      "Batch Sum": 202.24609375,
+      "accuracy": 0.734375,
+      "epoch": 0.13,
+      "step": 52
+    },
+    {
+      "epoch": 0.1325,
+      "grad_norm": 11.745606422424316,
+      "learning_rate": 4.565789473684211e-06,
+      "loss": 0.4841,
+      "step": 53
+    },
+    {
+      "Batch Sum": 197.15625,
+      "accuracy": 0.765625,
+      "epoch": 0.1325,
+      "step": 53
+    },
+    {
+      "Batch Sum": 200.75,
+      "accuracy": 0.71875,
+      "epoch": 0.1325,
+      "step": 53
+    },
+    {
+      "epoch": 0.135,
+      "grad_norm": 12.604297637939453,
+      "learning_rate": 4.552631578947369e-06,
+      "loss": 0.4502,
+      "step": 54
+    },
+    {
+      "Batch Sum": 214.22265625,
+      "accuracy": 0.6875,
+      "epoch": 0.135,
+      "step": 54
+    },
+    {
+      "Batch Sum": 207.84765625,
+      "accuracy": 0.78125,
+      "epoch": 0.135,
+      "step": 54
+    },
+    {
+      "epoch": 0.1375,
+      "grad_norm": 14.610075950622559,
+      "learning_rate": 4.539473684210527e-06,
+      "loss": 0.5449,
+      "step": 55
+    },
+    {
+      "Batch Sum": 221.5546875,
+      "accuracy": 0.875,
+      "epoch": 0.1375,
+      "step": 55
+    },
+    {
+      "Batch Sum": 236.11328125,
+      "accuracy": 0.765625,
+      "epoch": 0.1375,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 11.892423629760742,
+      "learning_rate": 4.526315789473685e-06,
+      "loss": 0.4002,
+      "step": 56
+    },
+    {
+      "Batch Sum": 246.265625,
+      "accuracy": 0.734375,
+      "epoch": 0.14,
+      "step": 56
+    },
+    {
+      "Batch Sum": 233.033203125,
+      "accuracy": 0.828125,
+      "epoch": 0.14,
+      "step": 56
+    },
+    {
+      "epoch": 0.1425,
+      "grad_norm": 13.1007719039917,
+      "learning_rate": 4.513157894736843e-06,
+      "loss": 0.4596,
+      "step": 57
+    },
+    {
+      "Batch Sum": 239.265625,
+      "accuracy": 0.78125,
+      "epoch": 0.1425,
+      "step": 57
+    },
+    {
+      "Batch Sum": 251.70703125,
+      "accuracy": 0.6875,
+      "epoch": 0.1425,
+      "step": 57
+    },
+    {
+      "epoch": 0.145,
+      "grad_norm": 14.813791275024414,
+      "learning_rate": 4.5e-06,
+      "loss": 0.5175,
+      "step": 58
+    },
+    {
+      "Batch Sum": 236.10546875,
+      "accuracy": 0.765625,
+      "epoch": 0.145,
+      "step": 58
+    },
+    {
+      "Batch Sum": 249.8046875,
+      "accuracy": 0.734375,
+      "epoch": 0.145,
+      "step": 58
+    },
+    {
+      "epoch": 0.1475,
+      "grad_norm": 14.486608505249023,
+      "learning_rate": 4.4868421052631584e-06,
+      "loss": 0.5035,
+      "step": 59
+    },
+    {
+      "Batch Sum": 241.12109375,
+      "accuracy": 0.78125,
+      "epoch": 0.1475,
+      "step": 59
+    },
+    {
+      "Batch Sum": 229.68359375,
+      "accuracy": 0.796875,
+      "epoch": 0.1475,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 12.024293899536133,
+      "learning_rate": 4.473684210526316e-06,
+      "loss": 0.4143,
+      "step": 60
+    },
+    {
+      "Batch Sum": 251.0,
+      "accuracy": 0.796875,
+      "epoch": 0.15,
+      "step": 60
+    },
+    {
+      "Batch Sum": 245.59765625,
+      "accuracy": 0.78125,
+      "epoch": 0.15,
+      "step": 60
+    },
+    {
+      "epoch": 0.1525,
+      "grad_norm": 11.371909141540527,
+      "learning_rate": 4.460526315789474e-06,
+      "loss": 0.3862,
+      "step": 61
+    },
+    {
+      "Batch Sum": 239.98828125,
+      "accuracy": 0.875,
+      "epoch": 0.1525,
+      "step": 61
+    },
+    {
+      "Batch Sum": 243.82421875,
+      "accuracy": 0.78125,
+      "epoch": 0.1525,
+      "step": 61
+    },
+    {
+      "epoch": 0.155,
+      "grad_norm": 11.827494621276855,
+      "learning_rate": 4.447368421052632e-06,
+      "loss": 0.3865,
+      "step": 62
+    },
+    {
+      "Batch Sum": 230.6640625,
+      "accuracy": 0.734375,
+      "epoch": 0.155,
+      "step": 62
+    },
+    {
+      "Batch Sum": 221.58984375,
+      "accuracy": 0.796875,
+      "epoch": 0.155,
+      "step": 62
+    },
+    {
+      "epoch": 0.1575,
+      "grad_norm": 11.711631774902344,
+      "learning_rate": 4.43421052631579e-06,
+      "loss": 0.4655,
+      "step": 63
+    },
+    {
+      "Batch Sum": 232.0703125,
+      "accuracy": 0.75,
+      "epoch": 0.1575,
+      "step": 63
+    },
+    {
+      "Batch Sum": 224.037109375,
+      "accuracy": 0.8125,
+      "epoch": 0.1575,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 11.687829971313477,
+      "learning_rate": 4.4210526315789476e-06,
+      "loss": 0.4065,
+      "step": 64
+    },
+    {
+      "Batch Sum": 232.53515625,
+      "accuracy": 0.671875,
+      "epoch": 0.16,
+      "step": 64
+    },
+    {
+      "Batch Sum": 225.68359375,
+      "accuracy": 0.734375,
+      "epoch": 0.16,
+      "step": 64
+    },
+    {
+      "epoch": 0.1625,
+      "grad_norm": 13.95382022857666,
+      "learning_rate": 4.407894736842105e-06,
+      "loss": 0.5705,
+      "step": 65
+    },
+    {
+      "Batch Sum": 237.1796875,
+      "accuracy": 0.859375,
+      "epoch": 0.1625,
+      "step": 65
+    },
+    {
+      "Batch Sum": 234.703125,
+      "accuracy": 0.84375,
+      "epoch": 0.1625,
+      "step": 65
+    },
+    {
+      "epoch": 0.165,
+      "grad_norm": 10.754307746887207,
+      "learning_rate": 4.394736842105263e-06,
+      "loss": 0.3935,
+      "step": 66
+    },
+    {
+      "Batch Sum": 216.4921875,
+      "accuracy": 0.8125,
+      "epoch": 0.165,
+      "step": 66
+    },
+    {
+      "Batch Sum": 238.1640625,
+      "accuracy": 0.828125,
+      "epoch": 0.165,
+      "step": 66
+    },
+    {
+      "epoch": 0.1675,
+      "grad_norm": 11.184181213378906,
+      "learning_rate": 4.381578947368421e-06,
+      "loss": 0.3747,
+      "step": 67
+    },
+    {
+      "Batch Sum": 211.755859375,
+      "accuracy": 0.828125,
+      "epoch": 0.1675,
+      "step": 67
+    },
+    {
+      "Batch Sum": 225.146484375,
+      "accuracy": 0.84375,
+      "epoch": 0.1675,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 10.842012405395508,
+      "learning_rate": 4.368421052631579e-06,
+      "loss": 0.3372,
+      "step": 68
+    },
+    {
+      "Batch Sum": 227.8291015625,
+      "accuracy": 0.796875,
+      "epoch": 0.17,
+      "step": 68
+    },
+    {
+      "Batch Sum": 214.9453125,
+      "accuracy": 0.78125,
+      "epoch": 0.17,
+      "step": 68
+    },
+    {
+      "epoch": 0.1725,
+      "grad_norm": 12.21465015411377,
+      "learning_rate": 4.3552631578947375e-06,
+      "loss": 0.4673,
+      "step": 69
+    },
+    {
+      "Batch Sum": 230.5546875,
+      "accuracy": 0.859375,
+      "epoch": 0.1725,
+      "step": 69
+    },
+    {
+      "Batch Sum": 229.95703125,
+      "accuracy": 0.796875,
+      "epoch": 0.1725,
+      "step": 69
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 12.969797134399414,
+      "learning_rate": 4.342105263157895e-06,
+      "loss": 0.4088,
+      "step": 70
+    },
+    {
+      "Batch Sum": 224.419921875,
+      "accuracy": 0.8125,
+      "epoch": 0.175,
+      "step": 70
+    },
+    {
+      "Batch Sum": 221.15234375,
+      "accuracy": 0.859375,
+      "epoch": 0.175,
+      "step": 70
+    },
+    {
+      "epoch": 0.1775,
+      "grad_norm": 12.190828323364258,
+      "learning_rate": 4.328947368421053e-06,
+      "loss": 0.4531,
+      "step": 71
+    },
+    {
+      "Batch Sum": 212.4345703125,
+      "accuracy": 0.78125,
+      "epoch": 0.1775,
+      "step": 71
+    },
+    {
+      "Batch Sum": 209.00390625,
+      "accuracy": 0.6875,
+      "epoch": 0.1775,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 15.806035041809082,
+      "learning_rate": 4.315789473684211e-06,
+      "loss": 0.4743,
+      "step": 72
+    },
+    {
+      "Batch Sum": 203.03515625,
+      "accuracy": 0.84375,
+      "epoch": 0.18,
+      "step": 72
+    },
+    {
+      "Batch Sum": 223.71875,
+      "accuracy": 0.84375,
+      "epoch": 0.18,
+      "step": 72
+    },
+    {
+      "epoch": 0.1825,
+      "grad_norm": 11.65701961517334,
+      "learning_rate": 4.302631578947369e-06,
+      "loss": 0.3151,
+      "step": 73
+    },
+    {
+      "Batch Sum": 206.0234375,
+      "accuracy": 0.75,
+      "epoch": 0.1825,
+      "step": 73
+    },
+    {
+      "Batch Sum": 213.287109375,
+      "accuracy": 0.8125,
+      "epoch": 0.1825,
+      "step": 73
+    },
+    {
+      "epoch": 0.185,
+      "grad_norm": 14.198211669921875,
+      "learning_rate": 4.289473684210527e-06,
+      "loss": 0.4365,
+      "step": 74
+    },
+    {
+      "Batch Sum": 209.15234375,
+      "accuracy": 0.8125,
+      "epoch": 0.185,
+      "step": 74
+    },
+    {
+      "Batch Sum": 219.087890625,
+      "accuracy": 0.78125,
+      "epoch": 0.185,
+      "step": 74
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 13.063102722167969,
+      "learning_rate": 4.276315789473684e-06,
+      "loss": 0.4194,
+      "step": 75
+    },
+    {
+      "Batch Sum": 206.705078125,
+      "accuracy": 0.828125,
+      "epoch": 0.1875,
+      "step": 75
+    },
+    {
+      "Batch Sum": 208.162109375,
+      "accuracy": 0.828125,
+      "epoch": 0.1875,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 12.24936580657959,
+      "learning_rate": 4.2631578947368425e-06,
+      "loss": 0.4291,
+      "step": 76
+    },
+    {
+      "Batch Sum": 198.51953125,
+      "accuracy": 0.703125,
+      "epoch": 0.19,
+      "step": 76
+    },
+    {
+      "Batch Sum": 197.17578125,
+      "accuracy": 0.78125,
+      "epoch": 0.19,
+      "step": 76
+    },
+    {
+      "epoch": 0.1925,
+      "grad_norm": 21.39528465270996,
+      "learning_rate": 4.25e-06,
+      "loss": 0.4907,
+      "step": 77
+    },
+    {
+      "Batch Sum": 189.150390625,
+      "accuracy": 0.75,
+      "epoch": 0.1925,
+      "step": 77
+    },
+    {
+      "Batch Sum": 189.181640625,
+      "accuracy": 0.8125,
+      "epoch": 0.1925,
+      "step": 77
+    },
+    {
+      "epoch": 0.195,
+      "grad_norm": 12.943084716796875,
+      "learning_rate": 4.236842105263158e-06,
+      "loss": 0.4025,
+      "step": 78
+    },
+    {
+      "Batch Sum": 199.0009765625,
+      "accuracy": 0.75,
+      "epoch": 0.195,
+      "step": 78
+    },
+    {
+      "Batch Sum": 197.556640625,
+      "accuracy": 0.71875,
+      "epoch": 0.195,
+      "step": 78
+    },
+    {
+      "epoch": 0.1975,
+      "grad_norm": 14.870590209960938,
+      "learning_rate": 4.223684210526316e-06,
+      "loss": 0.4874,
+      "step": 79
+    },
+    {
+      "Batch Sum": 187.6875,
+      "accuracy": 0.875,
+      "epoch": 0.1975,
+      "step": 79
+    },
+    {
+      "Batch Sum": 191.8916015625,
+      "accuracy": 0.765625,
+      "epoch": 0.1975,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 15.593913078308105,
+      "learning_rate": 4.210526315789474e-06,
+      "loss": 0.3468,
+      "step": 80
+    },
+    {
+      "Batch Sum": 173.8515625,
+      "accuracy": 0.703125,
+      "epoch": 0.2,
+      "step": 80
+    },
+    {
+      "Batch Sum": 185.919921875,
+      "accuracy": 0.8125,
+      "epoch": 0.2,
+      "step": 80
+    },
+    {
+      "epoch": 0.2025,
+      "grad_norm": 11.869901657104492,
+      "learning_rate": 4.197368421052632e-06,
+      "loss": 0.4181,
+      "step": 81
+    },
+    {
+      "Batch Sum": 173.52197265625,
+      "accuracy": 0.828125,
+      "epoch": 0.2025,
+      "step": 81
+    },
+    {
+      "Batch Sum": 164.21044921875,
+      "accuracy": 0.84375,
+      "epoch": 0.2025,
+      "step": 81
+    },
+    {
+      "epoch": 0.205,
+      "grad_norm": 11.220733642578125,
+      "learning_rate": 4.18421052631579e-06,
+      "loss": 0.385,
+      "step": 82
+    },
+    {
+      "Batch Sum": 158.6143798828125,
+      "accuracy": 0.90625,
+      "epoch": 0.205,
+      "step": 82
+    },
+    {
+      "Batch Sum": 185.5107421875,
+      "accuracy": 0.796875,
+      "epoch": 0.205,
+      "step": 82
+    },
+    {
+      "epoch": 0.2075,
+      "grad_norm": 11.525442123413086,
+      "learning_rate": 4.171052631578948e-06,
+      "loss": 0.3701,
+      "step": 83
+    },
+    {
+      "Batch Sum": 162.90478515625,
+      "accuracy": 0.734375,
+      "epoch": 0.2075,
+      "step": 83
+    },
+    {
+      "Batch Sum": 163.460693359375,
+      "accuracy": 0.78125,
+      "epoch": 0.2075,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 13.735023498535156,
+      "learning_rate": 4.157894736842106e-06,
+      "loss": 0.5058,
+      "step": 84
+    },
+    {
+      "Batch Sum": 172.984375,
+      "accuracy": 0.71875,
+      "epoch": 0.21,
+      "step": 84
+    },
+    {
+      "Batch Sum": 151.54931640625,
+      "accuracy": 0.84375,
+      "epoch": 0.21,
+      "step": 84
+    },
+    {
+      "epoch": 0.2125,
+      "grad_norm": 12.669657707214355,
+      "learning_rate": 4.144736842105263e-06,
+      "loss": 0.4216,
+      "step": 85
+    },
+    {
+      "Batch Sum": 156.759765625,
+      "accuracy": 0.78125,
+      "epoch": 0.2125,
+      "step": 85
+    },
+    {
+      "Batch Sum": 157.17529296875,
+      "accuracy": 0.765625,
+      "epoch": 0.2125,
+      "step": 85
+    },
+    {
+      "epoch": 0.215,
+      "grad_norm": 12.282760620117188,
+      "learning_rate": 4.1315789473684216e-06,
+      "loss": 0.4175,
+      "step": 86
+    },
+    {
+      "Batch Sum": 153.5771484375,
+      "accuracy": 0.78125,
+      "epoch": 0.215,
+      "step": 86
+    },
+    {
+      "Batch Sum": 147.1307373046875,
+      "accuracy": 0.8125,
+      "epoch": 0.215,
+      "step": 86
+    },
+    {
+      "epoch": 0.2175,
+      "grad_norm": 13.767319679260254,
+      "learning_rate": 4.118421052631579e-06,
+      "loss": 0.4217,
+      "step": 87
+    },
+    {
+      "Batch Sum": 151.193115234375,
+      "accuracy": 0.734375,
+      "epoch": 0.2175,
+      "step": 87
+    },
+    {
+      "Batch Sum": 143.0897216796875,
+      "accuracy": 0.8125,
+      "epoch": 0.2175,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 12.140963554382324,
+      "learning_rate": 4.105263157894737e-06,
+      "loss": 0.4242,
+      "step": 88
+    },
+    {
+      "Batch Sum": 145.87548828125,
+      "accuracy": 0.765625,
+      "epoch": 0.22,
+      "step": 88
+    },
+    {
+      "Batch Sum": 150.4423828125,
+      "accuracy": 0.828125,
+      "epoch": 0.22,
+      "step": 88
+    },
+    {
+      "epoch": 0.2225,
+      "grad_norm": 10.421849250793457,
+      "learning_rate": 4.092105263157895e-06,
+      "loss": 0.4024,
+      "step": 89
+    },
+    {
+      "Batch Sum": 164.34619140625,
+      "accuracy": 0.84375,
+      "epoch": 0.2225,
+      "step": 89
+    },
+    {
+      "Batch Sum": 151.582275390625,
+      "accuracy": 0.84375,
+      "epoch": 0.2225,
+      "step": 89
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 11.950529098510742,
+      "learning_rate": 4.078947368421053e-06,
+      "loss": 0.4162,
+      "step": 90
+    },
+    {
+      "Batch Sum": 177.598388671875,
+      "accuracy": 0.78125,
+      "epoch": 0.225,
+      "step": 90
+    },
+    {
+      "Batch Sum": 168.056884765625,
+      "accuracy": 0.75,
+      "epoch": 0.225,
+      "step": 90
+    },
+    {
+      "epoch": 0.2275,
+      "grad_norm": 13.336840629577637,
+      "learning_rate": 4.065789473684211e-06,
+      "loss": 0.4356,
+      "step": 91
+    },
+    {
+      "Batch Sum": 185.6875,
+      "accuracy": 0.828125,
+      "epoch": 0.2275,
+      "step": 91
+    },
+    {
+      "Batch Sum": 156.2733154296875,
+      "accuracy": 0.859375,
+      "epoch": 0.2275,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 10.884383201599121,
+      "learning_rate": 4.052631578947368e-06,
+      "loss": 0.3845,
+      "step": 92
+    },
+    {
+      "Batch Sum": 179.4698486328125,
+      "accuracy": 0.90625,
+      "epoch": 0.23,
+      "step": 92
+    },
+    {
+      "Batch Sum": 171.6319580078125,
+      "accuracy": 0.796875,
+      "epoch": 0.23,
+      "step": 92
+    },
+    {
+      "epoch": 0.2325,
+      "grad_norm": 11.024062156677246,
+      "learning_rate": 4.0394736842105265e-06,
+      "loss": 0.3715,
+      "step": 93
+    },
+    {
+      "Batch Sum": 170.8381805419922,
+      "accuracy": 0.75,
+      "epoch": 0.2325,
+      "step": 93
+    },
+    {
+      "Batch Sum": 173.384765625,
+      "accuracy": 0.8125,
+      "epoch": 0.2325,
+      "step": 93
+    },
+    {
+      "epoch": 0.235,
+      "grad_norm": 10.82882022857666,
+      "learning_rate": 4.026315789473684e-06,
+      "loss": 0.4289,
+      "step": 94
+    },
+    {
+      "Batch Sum": 164.244140625,
+      "accuracy": 0.75,
+      "epoch": 0.235,
+      "step": 94
+    },
+    {
+      "Batch Sum": 180.776123046875,
+      "accuracy": 0.796875,
+      "epoch": 0.235,
+      "step": 94
+    },
+    {
+      "epoch": 0.2375,
+      "grad_norm": 14.97029972076416,
+      "learning_rate": 4.013157894736842e-06,
+      "loss": 0.4478,
+      "step": 95
+    },
+    {
+      "Batch Sum": 174.9443359375,
+      "accuracy": 0.859375,
+      "epoch": 0.2375,
+      "step": 95
+    },
+    {
+      "Batch Sum": 168.7977294921875,
+      "accuracy": 0.84375,
+      "epoch": 0.2375,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 9.570242881774902,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.3363,
+      "step": 96
+    },
+    {
+      "Batch Sum": 162.29507446289062,
+      "accuracy": 0.75,
+      "epoch": 0.24,
+      "step": 96
+    },
+    {
+      "Batch Sum": 167.9951171875,
+      "accuracy": 0.734375,
+      "epoch": 0.24,
+      "step": 96
+    },
+    {
+      "epoch": 0.2425,
+      "grad_norm": 17.29254913330078,
+      "learning_rate": 3.986842105263158e-06,
+      "loss": 0.5527,
+      "step": 97
+    },
+    {
+      "Batch Sum": 154.8450927734375,
+      "accuracy": 0.859375,
+      "epoch": 0.2425,
+      "step": 97
+    },
+    {
+      "Batch Sum": 164.18359375,
+      "accuracy": 0.8125,
+      "epoch": 0.2425,
+      "step": 97
+    },
+    {
+      "epoch": 0.245,
+      "grad_norm": 10.639801025390625,
+      "learning_rate": 3.9736842105263165e-06,
+      "loss": 0.3685,
+      "step": 98
+    },
+    {
+      "Batch Sum": 161.786865234375,
+      "accuracy": 0.765625,
+      "epoch": 0.245,
+      "step": 98
+    },
+    {
+      "Batch Sum": 167.194091796875,
+      "accuracy": 0.796875,
+      "epoch": 0.245,
+      "step": 98
+    },
+    {
+      "epoch": 0.2475,
+      "grad_norm": 11.962891578674316,
+      "learning_rate": 3.960526315789474e-06,
+      "loss": 0.4209,
+      "step": 99
+    },
+    {
+      "Batch Sum": 156.116943359375,
+      "accuracy": 0.796875,
+      "epoch": 0.2475,
+      "step": 99
+    },
+    {
+      "Batch Sum": 158.47119140625,
+      "accuracy": 0.75,
+      "epoch": 0.2475,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 10.670126914978027,
+      "learning_rate": 3.947368421052632e-06,
+      "loss": 0.4568,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d77beb5f705beb14f5ec1440aa188d529fdd21781b719b9045947924bf26324
+size 5752

checkpoint-200/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-200/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "tlrm/Q25-1.5B-UC",
+  "architectures": [
+    "Qwen2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-200/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a5770f79f9c8e342f5e6379beb176e0d82f4a9189c7bbca2b65f85a460072a1
+size 4996670464

checkpoint-200/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d77ef3e65f6b7926011f10c862c92628de3ccfcd78e4155c5d554fba79c5ae9
+size 1178231192

checkpoint-200/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 6174863360
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "score.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-200/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n   {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,3833 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "Batch Sum": 52.814453125,
+      "accuracy": 0.546875,
+      "epoch": 0,
+      "step": 0
+    },
+    {
+      "Batch Sum": 52.524169921875,
+      "accuracy": 0.40625,
+      "epoch": 0,
+      "step": 0
+    },
+    {
+      "epoch": 0.0025,
+      "grad_norm": 12.003690719604492,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 0.714,
+      "step": 1
+    },
+    {
+      "Batch Sum": 52.9404296875,
+      "accuracy": 0.515625,
+      "epoch": 0.0025,
+      "step": 1
+    },
+    {
+      "Batch Sum": 48.3984375,
+      "accuracy": 0.625,
+      "epoch": 0.0025,
+      "step": 1
+    },
+    {
+      "epoch": 0.005,
+      "grad_norm": 14.317296981811523,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 0.6849,
+      "step": 2
+    },
+    {
+      "Batch Sum": 52.79443359375,
+      "accuracy": 0.484375,
+      "epoch": 0.005,
+      "step": 2
+    },
+    {
+      "Batch Sum": 53.980224609375,
+      "accuracy": 0.578125,
+      "epoch": 0.005,
+      "step": 2
+    },
+    {
+      "epoch": 0.0075,
+      "grad_norm": 21.00113296508789,
+      "learning_rate": 7.5e-07,
+      "loss": 0.7106,
+      "step": 3
+    },
+    {
+      "Batch Sum": 53.60833740234375,
+      "accuracy": 0.453125,
+      "epoch": 0.0075,
+      "step": 3
+    },
+    {
+      "Batch Sum": 52.896728515625,
+      "accuracy": 0.578125,
+      "epoch": 0.0075,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 13.431326866149902,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.6978,
+      "step": 4
+    },
+    {
+      "Batch Sum": 54.1025390625,
+      "accuracy": 0.65625,
+      "epoch": 0.01,
+      "step": 4
+    },
+    {
+      "Batch Sum": 54.279052734375,
+      "accuracy": 0.53125,
+      "epoch": 0.01,
+      "step": 4
+    },
+    {
+      "epoch": 0.0125,
+      "grad_norm": 13.951983451843262,
+      "learning_rate": 1.25e-06,
+      "loss": 0.6883,
+      "step": 5
+    },
+    {
+      "Batch Sum": 53.18408203125,
+      "accuracy": 0.578125,
+      "epoch": 0.0125,
+      "step": 5
+    },
+    {
+      "Batch Sum": 49.6630859375,
+      "accuracy": 0.53125,
+      "epoch": 0.0125,
+      "step": 5
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 11.490130424499512,
+      "learning_rate": 1.5e-06,
+      "loss": 0.6818,
+      "step": 6
+    },
+    {
+      "Batch Sum": 54.36865234375,
+      "accuracy": 0.546875,
+      "epoch": 0.015,
+      "step": 6
+    },
+    {
+      "Batch Sum": 53.27685546875,
+      "accuracy": 0.515625,
+      "epoch": 0.015,
+      "step": 6
+    },
+    {
+      "epoch": 0.0175,
+      "grad_norm": 18.882749557495117,
+      "learning_rate": 1.75e-06,
+      "loss": 0.7198,
+      "step": 7
+    },
+    {
+      "Batch Sum": 58.3974609375,
+      "accuracy": 0.421875,
+      "epoch": 0.0175,
+      "step": 7
+    },
+    {
+      "Batch Sum": 56.97265625,
+      "accuracy": 0.6875,
+      "epoch": 0.0175,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 12.89813232421875,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.6877,
+      "step": 8
+    },
+    {
+      "Batch Sum": 56.07861328125,
+      "accuracy": 0.625,
+      "epoch": 0.02,
+      "step": 8
+    },
+    {
+      "Batch Sum": 57.08154296875,
+      "accuracy": 0.609375,
+      "epoch": 0.02,
+      "step": 8
+    },
+    {
+      "epoch": 0.0225,
+      "grad_norm": 16.434814453125,
+      "learning_rate": 2.25e-06,
+      "loss": 0.6739,
+      "step": 9
+    },
+    {
+      "Batch Sum": 59.09326171875,
+      "accuracy": 0.453125,
+      "epoch": 0.0225,
+      "step": 9
+    },
+    {
+      "Batch Sum": 61.3369140625,
+      "accuracy": 0.546875,
+      "epoch": 0.0225,
+      "step": 9
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 13.62090015411377,
+      "learning_rate": 2.5e-06,
+      "loss": 0.6856,
+      "step": 10
+    },
+    {
+      "Batch Sum": 70.0703125,
+      "accuracy": 0.609375,
+      "epoch": 0.025,
+      "step": 10
+    },
+    {
+      "Batch Sum": 64.751953125,
+      "accuracy": 0.578125,
+      "epoch": 0.025,
+      "step": 10
+    },
+    {
+      "epoch": 0.0275,
+      "grad_norm": 13.072342872619629,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.6546,
+      "step": 11
+    },
+    {
+      "Batch Sum": 73.357421875,
+      "accuracy": 0.609375,
+      "epoch": 0.0275,
+      "step": 11
+    },
+    {
+      "Batch Sum": 72.185546875,
+      "accuracy": 0.578125,
+      "epoch": 0.0275,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 13.209249496459961,
+      "learning_rate": 3e-06,
+      "loss": 0.6519,
+      "step": 12
+    },
+    {
+      "Batch Sum": 77.0615234375,
+      "accuracy": 0.703125,
+      "epoch": 0.03,
+      "step": 12
+    },
+    {
+      "Batch Sum": 78.0577392578125,
+      "accuracy": 0.703125,
+      "epoch": 0.03,
+      "step": 12
+    },
+    {
+      "epoch": 0.0325,
+      "grad_norm": 12.592546463012695,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.6092,
+      "step": 13
+    },
+    {
+      "Batch Sum": 91.876953125,
+      "accuracy": 0.625,
+      "epoch": 0.0325,
+      "step": 13
+    },
+    {
+      "Batch Sum": 87.7666015625,
+      "accuracy": 0.6875,
+      "epoch": 0.0325,
+      "step": 13
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 14.43427848815918,
+      "learning_rate": 3.5e-06,
+      "loss": 0.601,
+      "step": 14
+    },
+    {
+      "Batch Sum": 97.5859375,
+      "accuracy": 0.65625,
+      "epoch": 0.035,
+      "step": 14
+    },
+    {
+      "Batch Sum": 107.59765625,
+      "accuracy": 0.71875,
+      "epoch": 0.035,
+      "step": 14
+    },
+    {
+      "epoch": 0.0375,
+      "grad_norm": 12.276965141296387,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.6045,
+      "step": 15
+    },
+    {
+      "Batch Sum": 111.8828125,
+      "accuracy": 0.59375,
+      "epoch": 0.0375,
+      "step": 15
+    },
+    {
+      "Batch Sum": 116.759765625,
+      "accuracy": 0.6875,
+      "epoch": 0.0375,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 12.269201278686523,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.6262,
+      "step": 16
+    },
+    {
+      "Batch Sum": 120.9140625,
+      "accuracy": 0.625,
+      "epoch": 0.04,
+      "step": 16
+    },
+    {
+      "Batch Sum": 125.150390625,
+      "accuracy": 0.703125,
+      "epoch": 0.04,
+      "step": 16
+    },
+    {
+      "epoch": 0.0425,
+      "grad_norm": 12.212128639221191,
+      "learning_rate": 4.25e-06,
+      "loss": 0.6265,
+      "step": 17
+    },
+    {
+      "Batch Sum": 136.623046875,
+      "accuracy": 0.71875,
+      "epoch": 0.0425,
+      "step": 17
+    },
+    {
+      "Batch Sum": 133.275390625,
+      "accuracy": 0.640625,
+      "epoch": 0.0425,
+      "step": 17
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 17.11771583557129,
+      "learning_rate": 4.5e-06,
+      "loss": 0.596,
+      "step": 18
+    },
+    {
+      "Batch Sum": 155.64453125,
+      "accuracy": 0.71875,
+      "epoch": 0.045,
+      "step": 18
+    },
+    {
+      "Batch Sum": 152.97265625,
+      "accuracy": 0.671875,
+      "epoch": 0.045,
+      "step": 18
+    },
+    {
+      "epoch": 0.0475,
+      "grad_norm": 17.395545959472656,
+      "learning_rate": 4.75e-06,
+      "loss": 0.6295,
+      "step": 19
+    },
+    {
+      "Batch Sum": 173.0703125,
+      "accuracy": 0.65625,
+      "epoch": 0.0475,
+      "step": 19
+    },
+    {
+      "Batch Sum": 173.05078125,
+      "accuracy": 0.671875,
+      "epoch": 0.0475,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 24.041831970214844,
+      "learning_rate": 5e-06,
+      "loss": 0.6095,
+      "step": 20
+    },
+    {
+      "Batch Sum": 191.30859375,
+      "accuracy": 0.765625,
+      "epoch": 0.05,
+      "step": 20
+    },
+    {
+      "Batch Sum": 196.74609375,
+      "accuracy": 0.6875,
+      "epoch": 0.05,
+      "step": 20
+    },
+    {
+      "epoch": 0.0525,
+      "grad_norm": 13.471965789794922,
+      "learning_rate": 4.986842105263158e-06,
+      "loss": 0.527,
+      "step": 21
+    },
+    {
+      "Batch Sum": 205.40625,
+      "accuracy": 0.703125,
+      "epoch": 0.0525,
+      "step": 21
+    },
+    {
+      "Batch Sum": 204.26953125,
+      "accuracy": 0.703125,
+      "epoch": 0.0525,
+      "step": 21
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 22.169654846191406,
+      "learning_rate": 4.973684210526316e-06,
+      "loss": 0.6532,
+      "step": 22
+    },
+    {
+      "Batch Sum": 208.29296875,
+      "accuracy": 0.578125,
+      "epoch": 0.055,
+      "step": 22
+    },
+    {
+      "Batch Sum": 208.50390625,
+      "accuracy": 0.75,
+      "epoch": 0.055,
+      "step": 22
+    },
+    {
+      "epoch": 0.0575,
+      "grad_norm": 21.459922790527344,
+      "learning_rate": 4.960526315789474e-06,
+      "loss": 0.6456,
+      "step": 23
+    },
+    {
+      "Batch Sum": 207.7421875,
+      "accuracy": 0.78125,
+      "epoch": 0.0575,
+      "step": 23
+    },
+    {
+      "Batch Sum": 205.7421875,
+      "accuracy": 0.625,
+      "epoch": 0.0575,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 12.531883239746094,
+      "learning_rate": 4.947368421052632e-06,
+      "loss": 0.5219,
+      "step": 24
+    },
+    {
+      "Batch Sum": 211.6640625,
+      "accuracy": 0.71875,
+      "epoch": 0.06,
+      "step": 24
+    },
+    {
+      "Batch Sum": 208.45703125,
+      "accuracy": 0.703125,
+      "epoch": 0.06,
+      "step": 24
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 16.02347755432129,
+      "learning_rate": 4.9342105263157895e-06,
+      "loss": 0.5895,
+      "step": 25
+    },
+    {
+      "Batch Sum": 213.375,
+      "accuracy": 0.640625,
+      "epoch": 0.0625,
+      "step": 25
+    },
+    {
+      "Batch Sum": 203.58203125,
+      "accuracy": 0.703125,
+      "epoch": 0.0625,
+      "step": 25
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 12.315845489501953,
+      "learning_rate": 4.921052631578948e-06,
+      "loss": 0.5732,
+      "step": 26
+    },
+    {
+      "Batch Sum": 202.23828125,
+      "accuracy": 0.734375,
+      "epoch": 0.065,
+      "step": 26
+    },
+    {
+      "Batch Sum": 197.6953125,
+      "accuracy": 0.703125,
+      "epoch": 0.065,
+      "step": 26
+    },
+    {
+      "epoch": 0.0675,
+      "grad_norm": 10.496895790100098,
+      "learning_rate": 4.907894736842106e-06,
+      "loss": 0.5467,
+      "step": 27
+    },
+    {
+      "Batch Sum": 183.37890625,
+      "accuracy": 0.703125,
+      "epoch": 0.0675,
+      "step": 27
+    },
+    {
+      "Batch Sum": 185.86328125,
+      "accuracy": 0.75,
+      "epoch": 0.0675,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 10.82455825805664,
+      "learning_rate": 4.894736842105264e-06,
+      "loss": 0.5028,
+      "step": 28
+    },
+    {
+      "Batch Sum": 179.2158203125,
+      "accuracy": 0.71875,
+      "epoch": 0.07,
+      "step": 28
+    },
+    {
+      "Batch Sum": 179.328125,
+      "accuracy": 0.734375,
+      "epoch": 0.07,
+      "step": 28
+    },
+    {
+      "epoch": 0.0725,
+      "grad_norm": 13.485640525817871,
+      "learning_rate": 4.881578947368422e-06,
+      "loss": 0.5516,
+      "step": 29
+    },
+    {
+      "Batch Sum": 174.9296875,
+      "accuracy": 0.703125,
+      "epoch": 0.0725,
+      "step": 29
+    },
+    {
+      "Batch Sum": 172.44921875,
+      "accuracy": 0.734375,
+      "epoch": 0.0725,
+      "step": 29
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 11.573375701904297,
+      "learning_rate": 4.8684210526315795e-06,
+      "loss": 0.5523,
+      "step": 30
+    },
+    {
+      "Batch Sum": 170.3046875,
+      "accuracy": 0.671875,
+      "epoch": 0.075,
+      "step": 30
+    },
+    {
+      "Batch Sum": 174.54296875,
+      "accuracy": 0.703125,
+      "epoch": 0.075,
+      "step": 30
+    },
+    {
+      "epoch": 0.0775,
+      "grad_norm": 10.271368026733398,
+      "learning_rate": 4.855263157894737e-06,
+      "loss": 0.5549,
+      "step": 31
+    },
+    {
+      "Batch Sum": 168.15625,
+      "accuracy": 0.75,
+      "epoch": 0.0775,
+      "step": 31
+    },
+    {
+      "Batch Sum": 169.49609375,
+      "accuracy": 0.671875,
+      "epoch": 0.0775,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 9.423661231994629,
+      "learning_rate": 4.842105263157895e-06,
+      "loss": 0.5279,
+      "step": 32
+    },
+    {
+      "Batch Sum": 166.53125,
+      "accuracy": 0.765625,
+      "epoch": 0.08,
+      "step": 32
+    },
+    {
+      "Batch Sum": 169.66015625,
+      "accuracy": 0.75,
+      "epoch": 0.08,
+      "step": 32
+    },
+    {
+      "epoch": 0.0825,
+      "grad_norm": 11.485343933105469,
+      "learning_rate": 4.828947368421053e-06,
+      "loss": 0.5109,
+      "step": 33
+    },
+    {
+      "Batch Sum": 169.38671875,
+      "accuracy": 0.6875,
+      "epoch": 0.0825,
+      "step": 33
+    },
+    {
+      "Batch Sum": 172.9375,
+      "accuracy": 0.796875,
+      "epoch": 0.0825,
+      "step": 33
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 10.612264633178711,
+      "learning_rate": 4.815789473684211e-06,
+      "loss": 0.555,
+      "step": 34
+    },
+    {
+      "Batch Sum": 179.78515625,
+      "accuracy": 0.71875,
+      "epoch": 0.085,
+      "step": 34
+    },
+    {
+      "Batch Sum": 173.041015625,
+      "accuracy": 0.75,
+      "epoch": 0.085,
+      "step": 34
+    },
+    {
+      "epoch": 0.0875,
+      "grad_norm": 9.249446868896484,
+      "learning_rate": 4.802631578947369e-06,
+      "loss": 0.528,
+      "step": 35
+    },
+    {
+      "Batch Sum": 169.671875,
+      "accuracy": 0.765625,
+      "epoch": 0.0875,
+      "step": 35
+    },
+    {
+      "Batch Sum": 184.578125,
+      "accuracy": 0.734375,
+      "epoch": 0.0875,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 8.817283630371094,
+      "learning_rate": 4.789473684210527e-06,
+      "loss": 0.452,
+      "step": 36
+    },
+    {
+      "Batch Sum": 182.33984375,
+      "accuracy": 0.765625,
+      "epoch": 0.09,
+      "step": 36
+    },
+    {
+      "Batch Sum": 190.103515625,
+      "accuracy": 0.75,
+      "epoch": 0.09,
+      "step": 36
+    },
+    {
+      "epoch": 0.0925,
+      "grad_norm": 18.01405906677246,
+      "learning_rate": 4.7763157894736844e-06,
+      "loss": 0.5748,
+      "step": 37
+    },
+    {
+      "Batch Sum": 192.9296875,
+      "accuracy": 0.796875,
+      "epoch": 0.0925,
+      "step": 37
+    },
+    {
+      "Batch Sum": 195.75390625,
+      "accuracy": 0.734375,
+      "epoch": 0.0925,
+      "step": 37
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 10.098393440246582,
+      "learning_rate": 4.763157894736842e-06,
+      "loss": 0.4995,
+      "step": 38
+    },
+    {
+      "Batch Sum": 199.21484375,
+      "accuracy": 0.75,
+      "epoch": 0.095,
+      "step": 38
+    },
+    {
+      "Batch Sum": 204.1640625,
+      "accuracy": 0.703125,
+      "epoch": 0.095,
+      "step": 38
+    },
+    {
+      "epoch": 0.0975,
+      "grad_norm": 13.419852256774902,
+      "learning_rate": 4.75e-06,
+      "loss": 0.5398,
+      "step": 39
+    },
+    {
+      "Batch Sum": 209.2578125,
+      "accuracy": 0.71875,
+      "epoch": 0.0975,
+      "step": 39
+    },
+    {
+      "Batch Sum": 213.6796875,
+      "accuracy": 0.640625,
+      "epoch": 0.0975,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 12.879420280456543,
+      "learning_rate": 4.736842105263158e-06,
+      "loss": 0.5389,
+      "step": 40
+    },
+    {
+      "Batch Sum": 220.0625,
+      "accuracy": 0.734375,
+      "epoch": 0.1,
+      "step": 40
+    },
+    {
+      "Batch Sum": 214.107421875,
+      "accuracy": 0.703125,
+      "epoch": 0.1,
+      "step": 40
+    },
+    {
+      "epoch": 0.1025,
+      "grad_norm": 10.593208312988281,
+      "learning_rate": 4.723684210526316e-06,
+      "loss": 0.4675,
+      "step": 41
+    },
+    {
+      "Batch Sum": 225.80078125,
+      "accuracy": 0.796875,
+      "epoch": 0.1025,
+      "step": 41
+    },
+    {
+      "Batch Sum": 218.39453125,
+      "accuracy": 0.765625,
+      "epoch": 0.1025,
+      "step": 41
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 10.301755905151367,
+      "learning_rate": 4.710526315789474e-06,
+      "loss": 0.4833,
+      "step": 42
+    },
+    {
+      "Batch Sum": 234.8203125,
+      "accuracy": 0.765625,
+      "epoch": 0.105,
+      "step": 42
+    },
+    {
+      "Batch Sum": 229.140625,
+      "accuracy": 0.734375,
+      "epoch": 0.105,
+      "step": 42
+    },
+    {
+      "epoch": 0.1075,
+      "grad_norm": 11.743901252746582,
+      "learning_rate": 4.697368421052632e-06,
+      "loss": 0.5026,
+      "step": 43
+    },
+    {
+      "Batch Sum": 226.81640625,
+      "accuracy": 0.734375,
+      "epoch": 0.1075,
+      "step": 43
+    },
+    {
+      "Batch Sum": 225.296875,
+      "accuracy": 0.75,
+      "epoch": 0.1075,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 13.593162536621094,
+      "learning_rate": 4.68421052631579e-06,
+      "loss": 0.5254,
+      "step": 44
+    },
+    {
+      "Batch Sum": 227.609375,
+      "accuracy": 0.703125,
+      "epoch": 0.11,
+      "step": 44
+    },
+    {
+      "Batch Sum": 216.0625,
+      "accuracy": 0.765625,
+      "epoch": 0.11,
+      "step": 44
+    },
+    {
+      "epoch": 0.1125,
+      "grad_norm": 11.014060974121094,
+      "learning_rate": 4.671052631578948e-06,
+      "loss": 0.4679,
+      "step": 45
+    },
+    {
+      "Batch Sum": 227.234375,
+      "accuracy": 0.640625,
+      "epoch": 0.1125,
+      "step": 45
+    },
+    {
+      "Batch Sum": 222.55078125,
+      "accuracy": 0.734375,
+      "epoch": 0.1125,
+      "step": 45
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 14.091309547424316,
+      "learning_rate": 4.657894736842106e-06,
+      "loss": 0.5738,
+      "step": 46
+    },
+    {
+      "Batch Sum": 217.4609375,
+      "accuracy": 0.6875,
+      "epoch": 0.115,
+      "step": 46
+    },
+    {
+      "Batch Sum": 224.85546875,
+      "accuracy": 0.671875,
+      "epoch": 0.115,
+      "step": 46
+    },
+    {
+      "epoch": 0.1175,
+      "grad_norm": 12.615903854370117,
+      "learning_rate": 4.6447368421052635e-06,
+      "loss": 0.5464,
+      "step": 47
+    },
+    {
+      "Batch Sum": 211.90625,
+      "accuracy": 0.75,
+      "epoch": 0.1175,
+      "step": 47
+    },
+    {
+      "Batch Sum": 207.115234375,
+      "accuracy": 0.734375,
+      "epoch": 0.1175,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 10.995285987854004,
+      "learning_rate": 4.631578947368421e-06,
+      "loss": 0.4911,
+      "step": 48
+    },
+    {
+      "Batch Sum": 198.1484375,
+      "accuracy": 0.734375,
+      "epoch": 0.12,
+      "step": 48
+    },
+    {
+      "Batch Sum": 195.65234375,
+      "accuracy": 0.765625,
+      "epoch": 0.12,
+      "step": 48
+    },
+    {
+      "epoch": 0.1225,
+      "grad_norm": 12.166397094726562,
+      "learning_rate": 4.618421052631579e-06,
+      "loss": 0.4656,
+      "step": 49
+    },
+    {
+      "Batch Sum": 192.26953125,
+      "accuracy": 0.703125,
+      "epoch": 0.1225,
+      "step": 49
+    },
+    {
+      "Batch Sum": 187.31640625,
+      "accuracy": 0.78125,
+      "epoch": 0.1225,
+      "step": 49
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 12.223002433776855,
+      "learning_rate": 4.605263157894737e-06,
+      "loss": 0.5363,
+      "step": 50
+    },
+    {
+      "Batch Sum": 192.75390625,
+      "accuracy": 0.796875,
+      "epoch": 0.125,
+      "step": 50
+    },
+    {
+      "Batch Sum": 182.095703125,
+      "accuracy": 0.734375,
+      "epoch": 0.125,
+      "step": 50
+    },
+    {
+      "epoch": 0.1275,
+      "grad_norm": 10.82153606414795,
+      "learning_rate": 4.592105263157895e-06,
+      "loss": 0.4713,
+      "step": 51
+    },
+    {
+      "Batch Sum": 187.1015625,
+      "accuracy": 0.71875,
+      "epoch": 0.1275,
+      "step": 51
+    },
+    {
+      "Batch Sum": 185.41796875,
+      "accuracy": 0.703125,
+      "epoch": 0.1275,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 13.1001558303833,
+      "learning_rate": 4.578947368421053e-06,
+      "loss": 0.5496,
+      "step": 52
+    },
+    {
+      "Batch Sum": 199.91015625,
+      "accuracy": 0.765625,
+      "epoch": 0.13,
+      "step": 52
+    },
+    {
+      "Batch Sum": 202.24609375,
+      "accuracy": 0.734375,
+      "epoch": 0.13,
+      "step": 52
+    },
+    {
+      "epoch": 0.1325,
+      "grad_norm": 11.745606422424316,
+      "learning_rate": 4.565789473684211e-06,
+      "loss": 0.4841,
+      "step": 53
+    },
+    {
+      "Batch Sum": 197.15625,
+      "accuracy": 0.765625,
+      "epoch": 0.1325,
+      "step": 53
+    },
+    {
+      "Batch Sum": 200.75,
+      "accuracy": 0.71875,
+      "epoch": 0.1325,
+      "step": 53
+    },
+    {
+      "epoch": 0.135,
+      "grad_norm": 12.604297637939453,
+      "learning_rate": 4.552631578947369e-06,
+      "loss": 0.4502,
+      "step": 54
+    },
+    {
+      "Batch Sum": 214.22265625,
+      "accuracy": 0.6875,
+      "epoch": 0.135,
+      "step": 54
+    },
+    {
+      "Batch Sum": 207.84765625,
+      "accuracy": 0.78125,
+      "epoch": 0.135,
+      "step": 54
+    },
+    {
+      "epoch": 0.1375,
+      "grad_norm": 14.610075950622559,
+      "learning_rate": 4.539473684210527e-06,
+      "loss": 0.5449,
+      "step": 55
+    },
+    {
+      "Batch Sum": 221.5546875,
+      "accuracy": 0.875,
+      "epoch": 0.1375,
+      "step": 55
+    },
+    {
+      "Batch Sum": 236.11328125,
+      "accuracy": 0.765625,
+      "epoch": 0.1375,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 11.892423629760742,
+      "learning_rate": 4.526315789473685e-06,
+      "loss": 0.4002,
+      "step": 56
+    },
+    {
+      "Batch Sum": 246.265625,
+      "accuracy": 0.734375,
+      "epoch": 0.14,
+      "step": 56
+    },
+    {
+      "Batch Sum": 233.033203125,
+      "accuracy": 0.828125,
+      "epoch": 0.14,
+      "step": 56
+    },
+    {
+      "epoch": 0.1425,
+      "grad_norm": 13.1007719039917,
+      "learning_rate": 4.513157894736843e-06,
+      "loss": 0.4596,
+      "step": 57
+    },
+    {
+      "Batch Sum": 239.265625,
+      "accuracy": 0.78125,
+      "epoch": 0.1425,
+      "step": 57
+    },
+    {
+      "Batch Sum": 251.70703125,
+      "accuracy": 0.6875,
+      "epoch": 0.1425,
+      "step": 57
+    },
+    {
+      "epoch": 0.145,
+      "grad_norm": 14.813791275024414,
+      "learning_rate": 4.5e-06,
+      "loss": 0.5175,
+      "step": 58
+    },
+    {
+      "Batch Sum": 236.10546875,
+      "accuracy": 0.765625,
+      "epoch": 0.145,
+      "step": 58
+    },
+    {
+      "Batch Sum": 249.8046875,
+      "accuracy": 0.734375,
+      "epoch": 0.145,
+      "step": 58
+    },
+    {
+      "epoch": 0.1475,
+      "grad_norm": 14.486608505249023,
+      "learning_rate": 4.4868421052631584e-06,
+      "loss": 0.5035,
+      "step": 59
+    },
+    {
+      "Batch Sum": 241.12109375,
+      "accuracy": 0.78125,
+      "epoch": 0.1475,
+      "step": 59
+    },
+    {
+      "Batch Sum": 229.68359375,
+      "accuracy": 0.796875,
+      "epoch": 0.1475,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 12.024293899536133,
+      "learning_rate": 4.473684210526316e-06,
+      "loss": 0.4143,
+      "step": 60
+    },
+    {
+      "Batch Sum": 251.0,
+      "accuracy": 0.796875,
+      "epoch": 0.15,
+      "step": 60
+    },
+    {
+      "Batch Sum": 245.59765625,
+      "accuracy": 0.78125,
+      "epoch": 0.15,
+      "step": 60
+    },
+    {
+      "epoch": 0.1525,
+      "grad_norm": 11.371909141540527,
+      "learning_rate": 4.460526315789474e-06,
+      "loss": 0.3862,
+      "step": 61
+    },
+    {
+      "Batch Sum": 239.98828125,
+      "accuracy": 0.875,
+      "epoch": 0.1525,
+      "step": 61
+    },
+    {
+      "Batch Sum": 243.82421875,
+      "accuracy": 0.78125,
+      "epoch": 0.1525,
+      "step": 61
+    },
+    {
+      "epoch": 0.155,
+      "grad_norm": 11.827494621276855,
+      "learning_rate": 4.447368421052632e-06,
+      "loss": 0.3865,
+      "step": 62
+    },
+    {
+      "Batch Sum": 230.6640625,
+      "accuracy": 0.734375,
+      "epoch": 0.155,
+      "step": 62
+    },
+    {
+      "Batch Sum": 221.58984375,
+      "accuracy": 0.796875,
+      "epoch": 0.155,
+      "step": 62
+    },
+    {
+      "epoch": 0.1575,
+      "grad_norm": 11.711631774902344,
+      "learning_rate": 4.43421052631579e-06,
+      "loss": 0.4655,
+      "step": 63
+    },
+    {
+      "Batch Sum": 232.0703125,
+      "accuracy": 0.75,
+      "epoch": 0.1575,
+      "step": 63
+    },
+    {
+      "Batch Sum": 224.037109375,
+      "accuracy": 0.8125,
+      "epoch": 0.1575,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 11.687829971313477,
+      "learning_rate": 4.4210526315789476e-06,
+      "loss": 0.4065,
+      "step": 64
+    },
+    {
+      "Batch Sum": 232.53515625,
+      "accuracy": 0.671875,
+      "epoch": 0.16,
+      "step": 64
+    },
+    {
+      "Batch Sum": 225.68359375,
+      "accuracy": 0.734375,
+      "epoch": 0.16,
+      "step": 64
+    },
+    {
+      "epoch": 0.1625,
+      "grad_norm": 13.95382022857666,
+      "learning_rate": 4.407894736842105e-06,
+      "loss": 0.5705,
+      "step": 65
+    },
+    {
+      "Batch Sum": 237.1796875,
+      "accuracy": 0.859375,
+      "epoch": 0.1625,
+      "step": 65
+    },
+    {
+      "Batch Sum": 234.703125,
+      "accuracy": 0.84375,
+      "epoch": 0.1625,
+      "step": 65
+    },
+    {
+      "epoch": 0.165,
+      "grad_norm": 10.754307746887207,
+      "learning_rate": 4.394736842105263e-06,
+      "loss": 0.3935,
+      "step": 66
+    },
+    {
+      "Batch Sum": 216.4921875,
+      "accuracy": 0.8125,
+      "epoch": 0.165,
+      "step": 66
+    },
+    {
+      "Batch Sum": 238.1640625,
+      "accuracy": 0.828125,
+      "epoch": 0.165,
+      "step": 66
+    },
+    {
+      "epoch": 0.1675,
+      "grad_norm": 11.184181213378906,
+      "learning_rate": 4.381578947368421e-06,
+      "loss": 0.3747,
+      "step": 67
+    },
+    {
+      "Batch Sum": 211.755859375,
+      "accuracy": 0.828125,
+      "epoch": 0.1675,
+      "step": 67
+    },
+    {
+      "Batch Sum": 225.146484375,
+      "accuracy": 0.84375,
+      "epoch": 0.1675,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 10.842012405395508,
+      "learning_rate": 4.368421052631579e-06,
+      "loss": 0.3372,
+      "step": 68
+    },
+    {
+      "Batch Sum": 227.8291015625,
+      "accuracy": 0.796875,
+      "epoch": 0.17,
+      "step": 68
+    },
+    {
+      "Batch Sum": 214.9453125,
+      "accuracy": 0.78125,
+      "epoch": 0.17,
+      "step": 68
+    },
+    {
+      "epoch": 0.1725,
+      "grad_norm": 12.21465015411377,
+      "learning_rate": 4.3552631578947375e-06,
+      "loss": 0.4673,
+      "step": 69
+    },
+    {
+      "Batch Sum": 230.5546875,
+      "accuracy": 0.859375,
+      "epoch": 0.1725,
+      "step": 69
+    },
+    {
+      "Batch Sum": 229.95703125,
+      "accuracy": 0.796875,
+      "epoch": 0.1725,
+      "step": 69
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 12.969797134399414,
+      "learning_rate": 4.342105263157895e-06,
+      "loss": 0.4088,
+      "step": 70
+    },
+    {
+      "Batch Sum": 224.419921875,
+      "accuracy": 0.8125,
+      "epoch": 0.175,
+      "step": 70
+    },
+    {
+      "Batch Sum": 221.15234375,
+      "accuracy": 0.859375,
+      "epoch": 0.175,
+      "step": 70
+    },
+    {
+      "epoch": 0.1775,
+      "grad_norm": 12.190828323364258,
+      "learning_rate": 4.328947368421053e-06,
+      "loss": 0.4531,
+      "step": 71
+    },
+    {
+      "Batch Sum": 212.4345703125,
+      "accuracy": 0.78125,
+      "epoch": 0.1775,
+      "step": 71
+    },
+    {
+      "Batch Sum": 209.00390625,
+      "accuracy": 0.6875,
+      "epoch": 0.1775,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 15.806035041809082,
+      "learning_rate": 4.315789473684211e-06,
+      "loss": 0.4743,
+      "step": 72
+    },
+    {
+      "Batch Sum": 203.03515625,
+      "accuracy": 0.84375,
+      "epoch": 0.18,
+      "step": 72
+    },
+    {
+      "Batch Sum": 223.71875,
+      "accuracy": 0.84375,
+      "epoch": 0.18,
+      "step": 72
+    },
+    {
+      "epoch": 0.1825,
+      "grad_norm": 11.65701961517334,
+      "learning_rate": 4.302631578947369e-06,
+      "loss": 0.3151,
+      "step": 73
+    },
+    {
+      "Batch Sum": 206.0234375,
+      "accuracy": 0.75,
+      "epoch": 0.1825,
+      "step": 73
+    },
+    {
+      "Batch Sum": 213.287109375,
+      "accuracy": 0.8125,
+      "epoch": 0.1825,
+      "step": 73
+    },
+    {
+      "epoch": 0.185,
+      "grad_norm": 14.198211669921875,
+      "learning_rate": 4.289473684210527e-06,
+      "loss": 0.4365,
+      "step": 74
+    },
+    {
+      "Batch Sum": 209.15234375,
+      "accuracy": 0.8125,
+      "epoch": 0.185,
+      "step": 74
+    },
+    {
+      "Batch Sum": 219.087890625,
+      "accuracy": 0.78125,
+      "epoch": 0.185,
+      "step": 74
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 13.063102722167969,
+      "learning_rate": 4.276315789473684e-06,
+      "loss": 0.4194,
+      "step": 75
+    },
+    {
+      "Batch Sum": 206.705078125,
+      "accuracy": 0.828125,
+      "epoch": 0.1875,
+      "step": 75
+    },
+    {
+      "Batch Sum": 208.162109375,
+      "accuracy": 0.828125,
+      "epoch": 0.1875,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 12.24936580657959,
+      "learning_rate": 4.2631578947368425e-06,
+      "loss": 0.4291,
+      "step": 76
+    },
+    {
+      "Batch Sum": 198.51953125,
+      "accuracy": 0.703125,
+      "epoch": 0.19,
+      "step": 76
+    },
+    {
+      "Batch Sum": 197.17578125,
+      "accuracy": 0.78125,
+      "epoch": 0.19,
+      "step": 76
+    },
+    {
+      "epoch": 0.1925,
+      "grad_norm": 21.39528465270996,
+      "learning_rate": 4.25e-06,
+      "loss": 0.4907,
+      "step": 77
+    },
+    {
+      "Batch Sum": 189.150390625,
+      "accuracy": 0.75,
+      "epoch": 0.1925,
+      "step": 77
+    },
+    {
+      "Batch Sum": 189.181640625,
+      "accuracy": 0.8125,
+      "epoch": 0.1925,
+      "step": 77
+    },
+    {
+      "epoch": 0.195,
+      "grad_norm": 12.943084716796875,
+      "learning_rate": 4.236842105263158e-06,
+      "loss": 0.4025,
+      "step": 78
+    },
+    {
+      "Batch Sum": 199.0009765625,
+      "accuracy": 0.75,
+      "epoch": 0.195,
+      "step": 78
+    },
+    {
+      "Batch Sum": 197.556640625,
+      "accuracy": 0.71875,
+      "epoch": 0.195,
+      "step": 78
+    },
+    {
+      "epoch": 0.1975,
+      "grad_norm": 14.870590209960938,
+      "learning_rate": 4.223684210526316e-06,
+      "loss": 0.4874,
+      "step": 79
+    },
+    {
+      "Batch Sum": 187.6875,
+      "accuracy": 0.875,
+      "epoch": 0.1975,
+      "step": 79
+    },
+    {
+      "Batch Sum": 191.8916015625,
+      "accuracy": 0.765625,
+      "epoch": 0.1975,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 15.593913078308105,
+      "learning_rate": 4.210526315789474e-06,
+      "loss": 0.3468,
+      "step": 80
+    },
+    {
+      "Batch Sum": 173.8515625,
+      "accuracy": 0.703125,
+      "epoch": 0.2,
+      "step": 80
+    },
+    {
+      "Batch Sum": 185.919921875,
+      "accuracy": 0.8125,
+      "epoch": 0.2,
+      "step": 80
+    },
+    {
+      "epoch": 0.2025,
+      "grad_norm": 11.869901657104492,
+      "learning_rate": 4.197368421052632e-06,
+      "loss": 0.4181,
+      "step": 81
+    },
+    {
+      "Batch Sum": 173.52197265625,
+      "accuracy": 0.828125,
+      "epoch": 0.2025,
+      "step": 81
+    },
+    {
+      "Batch Sum": 164.21044921875,
+      "accuracy": 0.84375,
+      "epoch": 0.2025,
+      "step": 81
+    },
+    {
+      "epoch": 0.205,
+      "grad_norm": 11.220733642578125,
+      "learning_rate": 4.18421052631579e-06,
+      "loss": 0.385,
+      "step": 82
+    },
+    {
+      "Batch Sum": 158.6143798828125,
+      "accuracy": 0.90625,
+      "epoch": 0.205,
+      "step": 82
+    },
+    {
+      "Batch Sum": 185.5107421875,
+      "accuracy": 0.796875,
+      "epoch": 0.205,
+      "step": 82
+    },
+    {
+      "epoch": 0.2075,
+      "grad_norm": 11.525442123413086,
+      "learning_rate": 4.171052631578948e-06,
+      "loss": 0.3701,
+      "step": 83
+    },
+    {
+      "Batch Sum": 162.90478515625,
+      "accuracy": 0.734375,
+      "epoch": 0.2075,
+      "step": 83
+    },
+    {
+      "Batch Sum": 163.460693359375,
+      "accuracy": 0.78125,
+      "epoch": 0.2075,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 13.735023498535156,
+      "learning_rate": 4.157894736842106e-06,
+      "loss": 0.5058,
+      "step": 84
+    },
+    {
+      "Batch Sum": 172.984375,
+      "accuracy": 0.71875,
+      "epoch": 0.21,
+      "step": 84
+    },
+    {
+      "Batch Sum": 151.54931640625,
+      "accuracy": 0.84375,
+      "epoch": 0.21,
+      "step": 84
+    },
+    {
+      "epoch": 0.2125,
+      "grad_norm": 12.669657707214355,
+      "learning_rate": 4.144736842105263e-06,
+      "loss": 0.4216,
+      "step": 85
+    },
+    {
+      "Batch Sum": 156.759765625,
+      "accuracy": 0.78125,
+      "epoch": 0.2125,
+      "step": 85
+    },
+    {
+      "Batch Sum": 157.17529296875,
+      "accuracy": 0.765625,
+      "epoch": 0.2125,
+      "step": 85
+    },
+    {
+      "epoch": 0.215,
+      "grad_norm": 12.282760620117188,
+      "learning_rate": 4.1315789473684216e-06,
+      "loss": 0.4175,
+      "step": 86
+    },
+    {
+      "Batch Sum": 153.5771484375,
+      "accuracy": 0.78125,
+      "epoch": 0.215,
+      "step": 86
+    },
+    {
+      "Batch Sum": 147.1307373046875,
+      "accuracy": 0.8125,
+      "epoch": 0.215,
+      "step": 86
+    },
+    {
+      "epoch": 0.2175,
+      "grad_norm": 13.767319679260254,
+      "learning_rate": 4.118421052631579e-06,
+      "loss": 0.4217,
+      "step": 87
+    },
+    {
+      "Batch Sum": 151.193115234375,
+      "accuracy": 0.734375,
+      "epoch": 0.2175,
+      "step": 87
+    },
+    {
+      "Batch Sum": 143.0897216796875,
+      "accuracy": 0.8125,
+      "epoch": 0.2175,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 12.140963554382324,
+      "learning_rate": 4.105263157894737e-06,
+      "loss": 0.4242,
+      "step": 88
+    },
+    {
+      "Batch Sum": 145.87548828125,
+      "accuracy": 0.765625,
+      "epoch": 0.22,
+      "step": 88
+    },
+    {
+      "Batch Sum": 150.4423828125,
+      "accuracy": 0.828125,
+      "epoch": 0.22,
+      "step": 88
+    },
+    {
+      "epoch": 0.2225,
+      "grad_norm": 10.421849250793457,
+      "learning_rate": 4.092105263157895e-06,
+      "loss": 0.4024,
+      "step": 89
+    },
+    {
+      "Batch Sum": 164.34619140625,
+      "accuracy": 0.84375,
+      "epoch": 0.2225,
+      "step": 89
+    },
+    {
+      "Batch Sum": 151.582275390625,
+      "accuracy": 0.84375,
+      "epoch": 0.2225,
+      "step": 89
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 11.950529098510742,
+      "learning_rate": 4.078947368421053e-06,
+      "loss": 0.4162,
+      "step": 90
+    },
+    {
+      "Batch Sum": 177.598388671875,
+      "accuracy": 0.78125,
+      "epoch": 0.225,
+      "step": 90
+    },
+    {
+      "Batch Sum": 168.056884765625,
+      "accuracy": 0.75,
+      "epoch": 0.225,
+      "step": 90
+    },
+    {
+      "epoch": 0.2275,
+      "grad_norm": 13.336840629577637,
+      "learning_rate": 4.065789473684211e-06,
+      "loss": 0.4356,
+      "step": 91
+    },
+    {
+      "Batch Sum": 185.6875,
+      "accuracy": 0.828125,
+      "epoch": 0.2275,
+      "step": 91
+    },
+    {
+      "Batch Sum": 156.2733154296875,
+      "accuracy": 0.859375,
+      "epoch": 0.2275,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 10.884383201599121,
+      "learning_rate": 4.052631578947368e-06,
+      "loss": 0.3845,
+      "step": 92
+    },
+    {
+      "Batch Sum": 179.4698486328125,
+      "accuracy": 0.90625,
+      "epoch": 0.23,
+      "step": 92
+    },
+    {
+      "Batch Sum": 171.6319580078125,
+      "accuracy": 0.796875,
+      "epoch": 0.23,
+      "step": 92
+    },
+    {
+      "epoch": 0.2325,
+      "grad_norm": 11.024062156677246,
+      "learning_rate": 4.0394736842105265e-06,
+      "loss": 0.3715,
+      "step": 93
+    },
+    {
+      "Batch Sum": 170.8381805419922,
+      "accuracy": 0.75,
+      "epoch": 0.2325,
+      "step": 93
+    },
+    {
+      "Batch Sum": 173.384765625,
+      "accuracy": 0.8125,
+      "epoch": 0.2325,
+      "step": 93
+    },
+    {
+      "epoch": 0.235,
+      "grad_norm": 10.82882022857666,
+      "learning_rate": 4.026315789473684e-06,
+      "loss": 0.4289,
+      "step": 94
+    },
+    {
+      "Batch Sum": 164.244140625,
+      "accuracy": 0.75,
+      "epoch": 0.235,
+      "step": 94
+    },
+    {
+      "Batch Sum": 180.776123046875,
+      "accuracy": 0.796875,
+      "epoch": 0.235,
+      "step": 94
+    },
+    {
+      "epoch": 0.2375,
+      "grad_norm": 14.97029972076416,
+      "learning_rate": 4.013157894736842e-06,
+      "loss": 0.4478,
+      "step": 95
+    },
+    {
+      "Batch Sum": 174.9443359375,
+      "accuracy": 0.859375,
+      "epoch": 0.2375,
+      "step": 95
+    },
+    {
+      "Batch Sum": 168.7977294921875,
+      "accuracy": 0.84375,
+      "epoch": 0.2375,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 9.570242881774902,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.3363,
+      "step": 96
+    },
+    {
+      "Batch Sum": 162.29507446289062,
+      "accuracy": 0.75,
+      "epoch": 0.24,
+      "step": 96
+    },
+    {
+      "Batch Sum": 167.9951171875,
+      "accuracy": 0.734375,
+      "epoch": 0.24,
+      "step": 96
+    },
+    {
+      "epoch": 0.2425,
+      "grad_norm": 17.29254913330078,
+      "learning_rate": 3.986842105263158e-06,
+      "loss": 0.5527,
+      "step": 97
+    },
+    {
+      "Batch Sum": 154.8450927734375,
+      "accuracy": 0.859375,
+      "epoch": 0.2425,
+      "step": 97
+    },
+    {
+      "Batch Sum": 164.18359375,
+      "accuracy": 0.8125,
+      "epoch": 0.2425,
+      "step": 97
+    },
+    {
+      "epoch": 0.245,
+      "grad_norm": 10.639801025390625,
+      "learning_rate": 3.9736842105263165e-06,
+      "loss": 0.3685,
+      "step": 98
+    },
+    {
+      "Batch Sum": 161.786865234375,
+      "accuracy": 0.765625,
+      "epoch": 0.245,
+      "step": 98
+    },
+    {
+      "Batch Sum": 167.194091796875,
+      "accuracy": 0.796875,
+      "epoch": 0.245,
+      "step": 98
+    },
+    {
+      "epoch": 0.2475,
+      "grad_norm": 11.962891578674316,
+      "learning_rate": 3.960526315789474e-06,
+      "loss": 0.4209,
+      "step": 99
+    },
+    {
+      "Batch Sum": 156.116943359375,
+      "accuracy": 0.796875,
+      "epoch": 0.2475,
+      "step": 99
+    },
+    {
+      "Batch Sum": 158.47119140625,
+      "accuracy": 0.75,
+      "epoch": 0.2475,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 10.670126914978027,
+      "learning_rate": 3.947368421052632e-06,
+      "loss": 0.4568,
+      "step": 100
+    },
+    {
+      "Batch Sum": 151.5293731689453,
+      "accuracy": 0.796875,
+      "epoch": 0.25,
+      "step": 100
+    },
+    {
+      "Batch Sum": 139.802490234375,
+      "accuracy": 0.75,
+      "epoch": 0.25,
+      "step": 100
+    },
+    {
+      "epoch": 0.2525,
+      "grad_norm": 10.257286071777344,
+      "learning_rate": 3.93421052631579e-06,
+      "loss": 0.4065,
+      "step": 101
+    },
+    {
+      "Batch Sum": 145.30331420898438,
+      "accuracy": 0.734375,
+      "epoch": 0.2525,
+      "step": 101
+    },
+    {
+      "Batch Sum": 142.9066162109375,
+      "accuracy": 0.84375,
+      "epoch": 0.2525,
+      "step": 101
+    },
+    {
+      "epoch": 0.255,
+      "grad_norm": 8.931941032409668,
+      "learning_rate": 3.921052631578947e-06,
+      "loss": 0.3486,
+      "step": 102
+    },
+    {
+      "Batch Sum": 129.5537109375,
+      "accuracy": 0.765625,
+      "epoch": 0.255,
+      "step": 102
+    },
+    {
+      "Batch Sum": 139.361328125,
+      "accuracy": 0.84375,
+      "epoch": 0.255,
+      "step": 102
+    },
+    {
+      "epoch": 0.2575,
+      "grad_norm": 11.819692611694336,
+      "learning_rate": 3.907894736842106e-06,
+      "loss": 0.4768,
+      "step": 103
+    },
+    {
+      "Batch Sum": 136.63330078125,
+      "accuracy": 0.859375,
+      "epoch": 0.2575,
+      "step": 103
+    },
+    {
+      "Batch Sum": 126.9212646484375,
+      "accuracy": 0.859375,
+      "epoch": 0.2575,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 10.561305046081543,
+      "learning_rate": 3.894736842105263e-06,
+      "loss": 0.3266,
+      "step": 104
+    },
+    {
+      "Batch Sum": 119.14749145507812,
+      "accuracy": 0.75,
+      "epoch": 0.26,
+      "step": 104
+    },
+    {
+      "Batch Sum": 115.628662109375,
+      "accuracy": 0.8125,
+      "epoch": 0.26,
+      "step": 104
+    },
+    {
+      "epoch": 0.2625,
+      "grad_norm": 28.31745719909668,
+      "learning_rate": 3.8815789473684214e-06,
+      "loss": 0.4407,
+      "step": 105
+    },
+    {
+      "Batch Sum": 127.26849365234375,
+      "accuracy": 0.796875,
+      "epoch": 0.2625,
+      "step": 105
+    },
+    {
+      "Batch Sum": 140.0218505859375,
+      "accuracy": 0.828125,
+      "epoch": 0.2625,
+      "step": 105
+    },
+    {
+      "epoch": 0.265,
+      "grad_norm": 12.298383712768555,
+      "learning_rate": 3.868421052631579e-06,
+      "loss": 0.4529,
+      "step": 106
+    },
+    {
+      "Batch Sum": 136.11062622070312,
+      "accuracy": 0.828125,
+      "epoch": 0.265,
+      "step": 106
+    },
+    {
+      "Batch Sum": 139.4700927734375,
+      "accuracy": 0.765625,
+      "epoch": 0.265,
+      "step": 106
+    },
+    {
+      "epoch": 0.2675,
+      "grad_norm": 11.664482116699219,
+      "learning_rate": 3.855263157894737e-06,
+      "loss": 0.4132,
+      "step": 107
+    },
+    {
+      "Batch Sum": 139.60125732421875,
+      "accuracy": 0.734375,
+      "epoch": 0.2675,
+      "step": 107
+    },
+    {
+      "Batch Sum": 137.16650390625,
+      "accuracy": 0.796875,
+      "epoch": 0.2675,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 10.46422290802002,
+      "learning_rate": 3.842105263157895e-06,
+      "loss": 0.3772,
+      "step": 108
+    },
+    {
+      "Batch Sum": 130.9759521484375,
+      "accuracy": 0.71875,
+      "epoch": 0.27,
+      "step": 108
+    },
+    {
+      "Batch Sum": 132.84173583984375,
+      "accuracy": 0.78125,
+      "epoch": 0.27,
+      "step": 108
+    },
+    {
+      "epoch": 0.2725,
+      "grad_norm": 11.786149024963379,
+      "learning_rate": 3.828947368421053e-06,
+      "loss": 0.4741,
+      "step": 109
+    },
+    {
+      "Batch Sum": 131.52923583984375,
+      "accuracy": 0.703125,
+      "epoch": 0.2725,
+      "step": 109
+    },
+    {
+      "Batch Sum": 133.90191650390625,
+      "accuracy": 0.78125,
+      "epoch": 0.2725,
+      "step": 109
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 13.17595100402832,
+      "learning_rate": 3.815789473684211e-06,
+      "loss": 0.521,
+      "step": 110
+    },
+    {
+      "Batch Sum": 108.73193359375,
+      "accuracy": 0.828125,
+      "epoch": 0.275,
+      "step": 110
+    },
+    {
+      "Batch Sum": 112.35197448730469,
+      "accuracy": 0.78125,
+      "epoch": 0.275,
+      "step": 110
+    },
+    {
+      "epoch": 0.2775,
+      "grad_norm": 10.771636009216309,
+      "learning_rate": 3.802631578947369e-06,
+      "loss": 0.3971,
+      "step": 111
+    },
+    {
+      "Batch Sum": 121.26911926269531,
+      "accuracy": 0.828125,
+      "epoch": 0.2775,
+      "step": 111
+    },
+    {
+      "Batch Sum": 126.85107421875,
+      "accuracy": 0.90625,
+      "epoch": 0.2775,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 9.355616569519043,
+      "learning_rate": 3.789473684210527e-06,
+      "loss": 0.3219,
+      "step": 112
+    },
+    {
+      "Batch Sum": 112.09989929199219,
+      "accuracy": 0.796875,
+      "epoch": 0.28,
+      "step": 112
+    },
+    {
+      "Batch Sum": 118.8616943359375,
+      "accuracy": 0.75,
+      "epoch": 0.28,
+      "step": 112
+    },
+    {
+      "epoch": 0.2825,
+      "grad_norm": 9.97263240814209,
+      "learning_rate": 3.7763157894736847e-06,
+      "loss": 0.4534,
+      "step": 113
+    },
+    {
+      "Batch Sum": 112.02926635742188,
+      "accuracy": 0.84375,
+      "epoch": 0.2825,
+      "step": 113
+    },
+    {
+      "Batch Sum": 128.11767578125,
+      "accuracy": 0.90625,
+      "epoch": 0.2825,
+      "step": 113
+    },
+    {
+      "epoch": 0.285,
+      "grad_norm": 8.701355934143066,
+      "learning_rate": 3.7631578947368426e-06,
+      "loss": 0.3521,
+      "step": 114
+    },
+    {
+      "Batch Sum": 114.733154296875,
+      "accuracy": 0.828125,
+      "epoch": 0.285,
+      "step": 114
+    },
+    {
+      "Batch Sum": 120.71221923828125,
+      "accuracy": 0.875,
+      "epoch": 0.285,
+      "step": 114
+    },
+    {
+      "epoch": 0.2875,
+      "grad_norm": 10.165462493896484,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.3602,
+      "step": 115
+    },
+    {
+      "Batch Sum": 130.4957275390625,
+      "accuracy": 0.875,
+      "epoch": 0.2875,
+      "step": 115
+    },
+    {
+      "Batch Sum": 129.851318359375,
+      "accuracy": 0.828125,
+      "epoch": 0.2875,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 8.85599422454834,
+      "learning_rate": 3.736842105263158e-06,
+      "loss": 0.3406,
+      "step": 116
+    },
+    {
+      "Batch Sum": 153.54833984375,
+      "accuracy": 0.828125,
+      "epoch": 0.29,
+      "step": 116
+    },
+    {
+      "Batch Sum": 117.29022216796875,
+      "accuracy": 0.734375,
+      "epoch": 0.29,
+      "step": 116
+    },
+    {
+      "epoch": 0.2925,
+      "grad_norm": 11.120735168457031,
+      "learning_rate": 3.723684210526316e-06,
+      "loss": 0.4414,
+      "step": 117
+    },
+    {
+      "Batch Sum": 133.2943115234375,
+      "accuracy": 0.8125,
+      "epoch": 0.2925,
+      "step": 117
+    },
+    {
+      "Batch Sum": 154.751708984375,
+      "accuracy": 0.765625,
+      "epoch": 0.2925,
+      "step": 117
+    },
+    {
+      "epoch": 0.295,
+      "grad_norm": 9.896623611450195,
+      "learning_rate": 3.710526315789474e-06,
+      "loss": 0.4025,
+      "step": 118
+    },
+    {
+      "Batch Sum": 146.9268798828125,
+      "accuracy": 0.796875,
+      "epoch": 0.295,
+      "step": 118
+    },
+    {
+      "Batch Sum": 157.404541015625,
+      "accuracy": 0.84375,
+      "epoch": 0.295,
+      "step": 118
+    },
+    {
+      "epoch": 0.2975,
+      "grad_norm": 12.310927391052246,
+      "learning_rate": 3.6973684210526317e-06,
+      "loss": 0.3888,
+      "step": 119
+    },
+    {
+      "Batch Sum": 177.720458984375,
+      "accuracy": 0.734375,
+      "epoch": 0.2975,
+      "step": 119
+    },
+    {
+      "Batch Sum": 154.5662841796875,
+      "accuracy": 0.828125,
+      "epoch": 0.2975,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 13.395303726196289,
+      "learning_rate": 3.6842105263157896e-06,
+      "loss": 0.4263,
+      "step": 120
+    },
+    {
+      "Batch Sum": 165.2161865234375,
+      "accuracy": 0.75,
+      "epoch": 0.3,
+      "step": 120
+    },
+    {
+      "Batch Sum": 154.25457763671875,
+      "accuracy": 0.765625,
+      "epoch": 0.3,
+      "step": 120
+    },
+    {
+      "epoch": 0.3025,
+      "grad_norm": 18.222015380859375,
+      "learning_rate": 3.6710526315789476e-06,
+      "loss": 0.5583,
+      "step": 121
+    },
+    {
+      "Batch Sum": 156.56472778320312,
+      "accuracy": 0.734375,
+      "epoch": 0.3025,
+      "step": 121
+    },
+    {
+      "Batch Sum": 154.8548583984375,
+      "accuracy": 0.8125,
+      "epoch": 0.3025,
+      "step": 121
+    },
+    {
+      "epoch": 0.305,
+      "grad_norm": 12.073637008666992,
+      "learning_rate": 3.657894736842106e-06,
+      "loss": 0.4433,
+      "step": 122
+    },
+    {
+      "Batch Sum": 191.345703125,
+      "accuracy": 0.8125,
+      "epoch": 0.305,
+      "step": 122
+    },
+    {
+      "Batch Sum": 194.02685546875,
+      "accuracy": 0.859375,
+      "epoch": 0.305,
+      "step": 122
+    },
+    {
+      "epoch": 0.3075,
+      "grad_norm": 11.347955703735352,
+      "learning_rate": 3.644736842105264e-06,
+      "loss": 0.3678,
+      "step": 123
+    },
+    {
+      "Batch Sum": 154.679443359375,
+      "accuracy": 0.859375,
+      "epoch": 0.3075,
+      "step": 123
+    },
+    {
+      "Batch Sum": 151.9825439453125,
+      "accuracy": 0.890625,
+      "epoch": 0.3075,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 9.588033676147461,
+      "learning_rate": 3.6315789473684217e-06,
+      "loss": 0.2785,
+      "step": 124
+    },
+    {
+      "Batch Sum": 163.2354278564453,
+      "accuracy": 0.796875,
+      "epoch": 0.31,
+      "step": 124
+    },
+    {
+      "Batch Sum": 176.15380859375,
+      "accuracy": 0.765625,
+      "epoch": 0.31,
+      "step": 124
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 13.149937629699707,
+      "learning_rate": 3.618421052631579e-06,
+      "loss": 0.4441,
+      "step": 125
+    },
+    {
+      "Batch Sum": 168.91845703125,
+      "accuracy": 0.765625,
+      "epoch": 0.3125,
+      "step": 125
+    },
+    {
+      "Batch Sum": 160.57781982421875,
+      "accuracy": 0.875,
+      "epoch": 0.3125,
+      "step": 125
+    },
+    {
+      "epoch": 0.315,
+      "grad_norm": 11.270033836364746,
+      "learning_rate": 3.605263157894737e-06,
+      "loss": 0.3817,
+      "step": 126
+    },
+    {
+      "Batch Sum": 154.63726806640625,
+      "accuracy": 0.796875,
+      "epoch": 0.315,
+      "step": 126
+    },
+    {
+      "Batch Sum": 161.947265625,
+      "accuracy": 0.8125,
+      "epoch": 0.315,
+      "step": 126
+    },
+    {
+      "epoch": 0.3175,
+      "grad_norm": 11.978543281555176,
+      "learning_rate": 3.592105263157895e-06,
+      "loss": 0.4194,
+      "step": 127
+    },
+    {
+      "Batch Sum": 158.22998046875,
+      "accuracy": 0.8125,
+      "epoch": 0.3175,
+      "step": 127
+    },
+    {
+      "Batch Sum": 155.70001220703125,
+      "accuracy": 0.703125,
+      "epoch": 0.3175,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 10.93179702758789,
+      "learning_rate": 3.578947368421053e-06,
+      "loss": 0.3997,
+      "step": 128
+    },
+    {
+      "Batch Sum": 156.26416015625,
+      "accuracy": 0.796875,
+      "epoch": 0.32,
+      "step": 128
+    },
+    {
+      "Batch Sum": 147.02413940429688,
+      "accuracy": 0.71875,
+      "epoch": 0.32,
+      "step": 128
+    },
+    {
+      "epoch": 0.3225,
+      "grad_norm": 11.40749740600586,
+      "learning_rate": 3.565789473684211e-06,
+      "loss": 0.4216,
+      "step": 129
+    },
+    {
+      "Batch Sum": 152.162109375,
+      "accuracy": 0.828125,
+      "epoch": 0.3225,
+      "step": 129
+    },
+    {
+      "Batch Sum": 156.4219970703125,
+      "accuracy": 0.828125,
+      "epoch": 0.3225,
+      "step": 129
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 10.318909645080566,
+      "learning_rate": 3.5526315789473687e-06,
+      "loss": 0.3745,
+      "step": 130
+    },
+    {
+      "Batch Sum": 157.092529296875,
+      "accuracy": 0.75,
+      "epoch": 0.325,
+      "step": 130
+    },
+    {
+      "Batch Sum": 152.626953125,
+      "accuracy": 0.6875,
+      "epoch": 0.325,
+      "step": 130
+    },
+    {
+      "epoch": 0.3275,
+      "grad_norm": 14.140223503112793,
+      "learning_rate": 3.5394736842105266e-06,
+      "loss": 0.5467,
+      "step": 131
+    },
+    {
+      "Batch Sum": 148.7054443359375,
+      "accuracy": 0.78125,
+      "epoch": 0.3275,
+      "step": 131
+    },
+    {
+      "Batch Sum": 156.0888671875,
+      "accuracy": 0.796875,
+      "epoch": 0.3275,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 10.437580108642578,
+      "learning_rate": 3.5263157894736846e-06,
+      "loss": 0.426,
+      "step": 132
+    },
+    {
+      "Batch Sum": 143.746337890625,
+      "accuracy": 0.875,
+      "epoch": 0.33,
+      "step": 132
+    },
+    {
+      "Batch Sum": 159.1666259765625,
+      "accuracy": 0.890625,
+      "epoch": 0.33,
+      "step": 132
+    },
+    {
+      "epoch": 0.3325,
+      "grad_norm": 9.603164672851562,
+      "learning_rate": 3.513157894736842e-06,
+      "loss": 0.3198,
+      "step": 133
+    },
+    {
+      "Batch Sum": 142.6644287109375,
+      "accuracy": 0.765625,
+      "epoch": 0.3325,
+      "step": 133
+    },
+    {
+      "Batch Sum": 138.824951171875,
+      "accuracy": 0.734375,
+      "epoch": 0.3325,
+      "step": 133
+    },
+    {
+      "epoch": 0.335,
+      "grad_norm": 10.18635368347168,
+      "learning_rate": 3.5e-06,
+      "loss": 0.4675,
+      "step": 134
+    },
+    {
+      "Batch Sum": 145.2435302734375,
+      "accuracy": 0.828125,
+      "epoch": 0.335,
+      "step": 134
+    },
+    {
+      "Batch Sum": 133.55718994140625,
+      "accuracy": 0.84375,
+      "epoch": 0.335,
+      "step": 134
+    },
+    {
+      "epoch": 0.3375,
+      "grad_norm": 8.98958683013916,
+      "learning_rate": 3.486842105263158e-06,
+      "loss": 0.394,
+      "step": 135
+    },
+    {
+      "Batch Sum": 144.40631103515625,
+      "accuracy": 0.828125,
+      "epoch": 0.3375,
+      "step": 135
+    },
+    {
+      "Batch Sum": 155.13470458984375,
+      "accuracy": 0.828125,
+      "epoch": 0.3375,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 10.116023063659668,
+      "learning_rate": 3.473684210526316e-06,
+      "loss": 0.3919,
+      "step": 136
+    },
+    {
+      "Batch Sum": 157.0986328125,
+      "accuracy": 0.828125,
+      "epoch": 0.34,
+      "step": 136
+    },
+    {
+      "Batch Sum": 151.594970703125,
+      "accuracy": 0.84375,
+      "epoch": 0.34,
+      "step": 136
+    },
+    {
+      "epoch": 0.3425,
+      "grad_norm": 9.4917573928833,
+      "learning_rate": 3.460526315789474e-06,
+      "loss": 0.3728,
+      "step": 137
+    },
+    {
+      "Batch Sum": 144.12567138671875,
+      "accuracy": 0.828125,
+      "epoch": 0.3425,
+      "step": 137
+    },
+    {
+      "Batch Sum": 158.22021484375,
+      "accuracy": 0.828125,
+      "epoch": 0.3425,
+      "step": 137
+    },
+    {
+      "epoch": 0.345,
+      "grad_norm": 9.91769027709961,
+      "learning_rate": 3.447368421052632e-06,
+      "loss": 0.3612,
+      "step": 138
+    },
+    {
+      "Batch Sum": 163.3560791015625,
+      "accuracy": 0.765625,
+      "epoch": 0.345,
+      "step": 138
+    },
+    {
+      "Batch Sum": 165.13037109375,
+      "accuracy": 0.8125,
+      "epoch": 0.345,
+      "step": 138
+    },
+    {
+      "epoch": 0.3475,
+      "grad_norm": 11.594426155090332,
+      "learning_rate": 3.43421052631579e-06,
+      "loss": 0.4229,
+      "step": 139
+    },
+    {
+      "Batch Sum": 176.0669708251953,
+      "accuracy": 0.75,
+      "epoch": 0.3475,
+      "step": 139
+    },
+    {
+      "Batch Sum": 170.3831787109375,
+      "accuracy": 0.8125,
+      "epoch": 0.3475,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 12.000874519348145,
+      "learning_rate": 3.421052631578948e-06,
+      "loss": 0.448,
+      "step": 140
+    },
+    {
+      "Batch Sum": 173.9276123046875,
+      "accuracy": 0.8125,
+      "epoch": 0.35,
+      "step": 140
+    },
+    {
+      "Batch Sum": 171.8037109375,
+      "accuracy": 0.78125,
+      "epoch": 0.35,
+      "step": 140
+    },
+    {
+      "epoch": 0.3525,
+      "grad_norm": 13.811454772949219,
+      "learning_rate": 3.4078947368421057e-06,
+      "loss": 0.4739,
+      "step": 141
+    },
+    {
+      "Batch Sum": 167.4185791015625,
+      "accuracy": 0.796875,
+      "epoch": 0.3525,
+      "step": 141
+    },
+    {
+      "Batch Sum": 169.88824462890625,
+      "accuracy": 0.734375,
+      "epoch": 0.3525,
+      "step": 141
+    },
+    {
+      "epoch": 0.355,
+      "grad_norm": 12.386519432067871,
+      "learning_rate": 3.3947368421052636e-06,
+      "loss": 0.4468,
+      "step": 142
+    },
+    {
+      "Batch Sum": 172.253173828125,
+      "accuracy": 0.875,
+      "epoch": 0.355,
+      "step": 142
+    },
+    {
+      "Batch Sum": 179.5269775390625,
+      "accuracy": 0.765625,
+      "epoch": 0.355,
+      "step": 142
+    },
+    {
+      "epoch": 0.3575,
+      "grad_norm": 10.997251510620117,
+      "learning_rate": 3.381578947368421e-06,
+      "loss": 0.3703,
+      "step": 143
+    },
+    {
+      "Batch Sum": 177.33450317382812,
+      "accuracy": 0.859375,
+      "epoch": 0.3575,
+      "step": 143
+    },
+    {
+      "Batch Sum": 168.30322265625,
+      "accuracy": 0.796875,
+      "epoch": 0.3575,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 10.775482177734375,
+      "learning_rate": 3.368421052631579e-06,
+      "loss": 0.3419,
+      "step": 144
+    },
+    {
+      "Batch Sum": 177.181396484375,
+      "accuracy": 0.78125,
+      "epoch": 0.36,
+      "step": 144
+    },
+    {
+      "Batch Sum": 179.53369140625,
+      "accuracy": 0.8125,
+      "epoch": 0.36,
+      "step": 144
+    },
+    {
+      "epoch": 0.3625,
+      "grad_norm": 11.77710247039795,
+      "learning_rate": 3.355263157894737e-06,
+      "loss": 0.442,
+      "step": 145
+    },
+    {
+      "Batch Sum": 163.1304931640625,
+      "accuracy": 0.84375,
+      "epoch": 0.3625,
+      "step": 145
+    },
+    {
+      "Batch Sum": 173.8359375,
+      "accuracy": 0.78125,
+      "epoch": 0.3625,
+      "step": 145
+    },
+    {
+      "epoch": 0.365,
+      "grad_norm": 10.837456703186035,
+      "learning_rate": 3.342105263157895e-06,
+      "loss": 0.3772,
+      "step": 146
+    },
+    {
+      "Batch Sum": 168.785888671875,
+      "accuracy": 0.765625,
+      "epoch": 0.365,
+      "step": 146
+    },
+    {
+      "Batch Sum": 162.473388671875,
+      "accuracy": 0.796875,
+      "epoch": 0.365,
+      "step": 146
+    },
+    {
+      "epoch": 0.3675,
+      "grad_norm": 12.898738861083984,
+      "learning_rate": 3.3289473684210528e-06,
+      "loss": 0.4284,
+      "step": 147
+    },
+    {
+      "Batch Sum": 155.8890380859375,
+      "accuracy": 0.8125,
+      "epoch": 0.3675,
+      "step": 147
+    },
+    {
+      "Batch Sum": 163.2218017578125,
+      "accuracy": 0.84375,
+      "epoch": 0.3675,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 10.30620288848877,
+      "learning_rate": 3.3157894736842107e-06,
+      "loss": 0.3338,
+      "step": 148
+    },
+    {
+      "Batch Sum": 179.05615234375,
+      "accuracy": 0.84375,
+      "epoch": 0.37,
+      "step": 148
+    },
+    {
+      "Batch Sum": 165.72119140625,
+      "accuracy": 0.8125,
+      "epoch": 0.37,
+      "step": 148
+    },
+    {
+      "epoch": 0.3725,
+      "grad_norm": 10.406338691711426,
+      "learning_rate": 3.302631578947369e-06,
+      "loss": 0.3486,
+      "step": 149
+    },
+    {
+      "Batch Sum": 153.40414428710938,
+      "accuracy": 0.859375,
+      "epoch": 0.3725,
+      "step": 149
+    },
+    {
+      "Batch Sum": 157.75411987304688,
+      "accuracy": 0.796875,
+      "epoch": 0.3725,
+      "step": 149
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 11.733957290649414,
+      "learning_rate": 3.289473684210527e-06,
+      "loss": 0.36,
+      "step": 150
+    },
+    {
+      "Batch Sum": 179.1650390625,
+      "accuracy": 0.875,
+      "epoch": 0.375,
+      "step": 150
+    },
+    {
+      "Batch Sum": 178.9234619140625,
+      "accuracy": 0.875,
+      "epoch": 0.375,
+      "step": 150
+    },
+    {
+      "epoch": 0.3775,
+      "grad_norm": 9.269570350646973,
+      "learning_rate": 3.276315789473685e-06,
+      "loss": 0.2708,
+      "step": 151
+    },
+    {
+      "Batch Sum": 179.40478515625,
+      "accuracy": 0.84375,
+      "epoch": 0.3775,
+      "step": 151
+    },
+    {
+      "Batch Sum": 162.3435516357422,
+      "accuracy": 0.8125,
+      "epoch": 0.3775,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 12.036487579345703,
+      "learning_rate": 3.2631578947368423e-06,
+      "loss": 0.3789,
+      "step": 152
+    },
+    {
+      "Batch Sum": 154.46905517578125,
+      "accuracy": 0.84375,
+      "epoch": 0.38,
+      "step": 152
+    },
+    {
+      "Batch Sum": 176.2408447265625,
+      "accuracy": 0.8125,
+      "epoch": 0.38,
+      "step": 152
+    },
+    {
+      "epoch": 0.3825,
+      "grad_norm": 10.829084396362305,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.3816,
+      "step": 153
+    },
+    {
+      "Batch Sum": 171.27947998046875,
+      "accuracy": 0.75,
+      "epoch": 0.3825,
+      "step": 153
+    },
+    {
+      "Batch Sum": 181.0279541015625,
+      "accuracy": 0.859375,
+      "epoch": 0.3825,
+      "step": 153
+    },
+    {
+      "epoch": 0.385,
+      "grad_norm": 13.027417182922363,
+      "learning_rate": 3.236842105263158e-06,
+      "loss": 0.4191,
+      "step": 154
+    },
+    {
+      "Batch Sum": 173.9217529296875,
+      "accuracy": 0.8125,
+      "epoch": 0.385,
+      "step": 154
+    },
+    {
+      "Batch Sum": 170.60922241210938,
+      "accuracy": 0.765625,
+      "epoch": 0.385,
+      "step": 154
+    },
+    {
+      "epoch": 0.3875,
+      "grad_norm": 15.362863540649414,
+      "learning_rate": 3.223684210526316e-06,
+      "loss": 0.4455,
+      "step": 155
+    },
+    {
+      "Batch Sum": 185.8359375,
+      "accuracy": 0.875,
+      "epoch": 0.3875,
+      "step": 155
+    },
+    {
+      "Batch Sum": 175.69873046875,
+      "accuracy": 0.859375,
+      "epoch": 0.3875,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 11.39478874206543,
+      "learning_rate": 3.210526315789474e-06,
+      "loss": 0.3245,
+      "step": 156
+    },
+    {
+      "Batch Sum": 187.887451171875,
+      "accuracy": 0.796875,
+      "epoch": 0.39,
+      "step": 156
+    },
+    {
+      "Batch Sum": 176.8115234375,
+      "accuracy": 0.8125,
+      "epoch": 0.39,
+      "step": 156
+    },
+    {
+      "epoch": 0.3925,
+      "grad_norm": 12.699715614318848,
+      "learning_rate": 3.197368421052632e-06,
+      "loss": 0.3727,
+      "step": 157
+    },
+    {
+      "Batch Sum": 174.041015625,
+      "accuracy": 0.875,
+      "epoch": 0.3925,
+      "step": 157
+    },
+    {
+      "Batch Sum": 175.4111328125,
+      "accuracy": 0.734375,
+      "epoch": 0.3925,
+      "step": 157
+    },
+    {
+      "epoch": 0.395,
+      "grad_norm": 13.248059272766113,
+      "learning_rate": 3.1842105263157898e-06,
+      "loss": 0.434,
+      "step": 158
+    },
+    {
+      "Batch Sum": 163.93408203125,
+      "accuracy": 0.796875,
+      "epoch": 0.395,
+      "step": 158
+    },
+    {
+      "Batch Sum": 172.42626953125,
+      "accuracy": 0.84375,
+      "epoch": 0.395,
+      "step": 158
+    },
+    {
+      "epoch": 0.3975,
+      "grad_norm": 12.247123718261719,
+      "learning_rate": 3.1710526315789477e-06,
+      "loss": 0.3552,
+      "step": 159
+    },
+    {
+      "Batch Sum": 159.5538330078125,
+      "accuracy": 0.796875,
+      "epoch": 0.3975,
+      "step": 159
+    },
+    {
+      "Batch Sum": 172.398193359375,
+      "accuracy": 0.84375,
+      "epoch": 0.3975,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 13.754870414733887,
+      "learning_rate": 3.157894736842105e-06,
+      "loss": 0.4638,
+      "step": 160
+    },
+    {
+      "Batch Sum": 179.1923828125,
+      "accuracy": 0.859375,
+      "epoch": 0.4,
+      "step": 160
+    },
+    {
+      "Batch Sum": 161.6951904296875,
+      "accuracy": 0.8125,
+      "epoch": 0.4,
+      "step": 160
+    },
+    {
+      "epoch": 0.4025,
+      "grad_norm": 9.910033226013184,
+      "learning_rate": 3.144736842105263e-06,
+      "loss": 0.3066,
+      "step": 161
+    },
+    {
+      "Batch Sum": 169.45782470703125,
+      "accuracy": 0.859375,
+      "epoch": 0.4025,
+      "step": 161
+    },
+    {
+      "Batch Sum": 157.14697265625,
+      "accuracy": 0.890625,
+      "epoch": 0.4025,
+      "step": 161
+    },
+    {
+      "epoch": 0.405,
+      "grad_norm": 9.645856857299805,
+      "learning_rate": 3.131578947368421e-06,
+      "loss": 0.2836,
+      "step": 162
+    },
+    {
+      "Batch Sum": 153.429443359375,
+      "accuracy": 0.75,
+      "epoch": 0.405,
+      "step": 162
+    },
+    {
+      "Batch Sum": 159.56504821777344,
+      "accuracy": 0.859375,
+      "epoch": 0.405,
+      "step": 162
+    },
+    {
+      "epoch": 0.4075,
+      "grad_norm": 11.657127380371094,
+      "learning_rate": 3.1184210526315793e-06,
+      "loss": 0.4141,
+      "step": 163
+    },
+    {
+      "Batch Sum": 157.7459716796875,
+      "accuracy": 0.734375,
+      "epoch": 0.4075,
+      "step": 163
+    },
+    {
+      "Batch Sum": 163.69723510742188,
+      "accuracy": 0.796875,
+      "epoch": 0.4075,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 13.670110702514648,
+      "learning_rate": 3.1052631578947372e-06,
+      "loss": 0.4772,
+      "step": 164
+    },
+    {
+      "Batch Sum": 157.6031494140625,
+      "accuracy": 0.890625,
+      "epoch": 0.41,
+      "step": 164
+    },
+    {
+      "Batch Sum": 172.3399658203125,
+      "accuracy": 0.828125,
+      "epoch": 0.41,
+      "step": 164
+    },
+    {
+      "epoch": 0.4125,
+      "grad_norm": 9.068910598754883,
+      "learning_rate": 3.092105263157895e-06,
+      "loss": 0.2752,
+      "step": 165
+    },
+    {
+      "Batch Sum": 160.44140625,
+      "accuracy": 0.859375,
+      "epoch": 0.4125,
+      "step": 165
+    },
+    {
+      "Batch Sum": 169.0107421875,
+      "accuracy": 0.71875,
+      "epoch": 0.4125,
+      "step": 165
+    },
+    {
+      "epoch": 0.415,
+      "grad_norm": 12.532942771911621,
+      "learning_rate": 3.078947368421053e-06,
+      "loss": 0.4162,
+      "step": 166
+    },
+    {
+      "Batch Sum": 150.088623046875,
+      "accuracy": 0.90625,
+      "epoch": 0.415,
+      "step": 166
+    },
+    {
+      "Batch Sum": 163.49560546875,
+      "accuracy": 0.765625,
+      "epoch": 0.415,
+      "step": 166
+    },
+    {
+      "epoch": 0.4175,
+      "grad_norm": 11.255102157592773,
+      "learning_rate": 3.065789473684211e-06,
+      "loss": 0.3426,
+      "step": 167
+    },
+    {
+      "Batch Sum": 158.72216796875,
+      "accuracy": 0.78125,
+      "epoch": 0.4175,
+      "step": 167
+    },
+    {
+      "Batch Sum": 157.4320068359375,
+      "accuracy": 0.75,
+      "epoch": 0.4175,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 11.509016036987305,
+      "learning_rate": 3.052631578947369e-06,
+      "loss": 0.3974,
+      "step": 168
+    },
+    {
+      "Batch Sum": 170.9871826171875,
+      "accuracy": 0.859375,
+      "epoch": 0.42,
+      "step": 168
+    },
+    {
+      "Batch Sum": 151.966796875,
+      "accuracy": 0.859375,
+      "epoch": 0.42,
+      "step": 168
+    },
+    {
+      "epoch": 0.4225,
+      "grad_norm": 11.246017456054688,
+      "learning_rate": 3.0394736842105268e-06,
+      "loss": 0.346,
+      "step": 169
+    },
+    {
+      "Batch Sum": 141.69485473632812,
+      "accuracy": 0.8125,
+      "epoch": 0.4225,
+      "step": 169
+    },
+    {
+      "Batch Sum": 177.1005859375,
+      "accuracy": 0.84375,
+      "epoch": 0.4225,
+      "step": 169
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 12.605325698852539,
+      "learning_rate": 3.0263157894736843e-06,
+      "loss": 0.3574,
+      "step": 170
+    },
+    {
+      "Batch Sum": 158.830078125,
+      "accuracy": 0.796875,
+      "epoch": 0.425,
+      "step": 170
+    },
+    {
+      "Batch Sum": 171.9595947265625,
+      "accuracy": 0.78125,
+      "epoch": 0.425,
+      "step": 170
+    },
+    {
+      "epoch": 0.4275,
+      "grad_norm": 11.472408294677734,
+      "learning_rate": 3.013157894736842e-06,
+      "loss": 0.3778,
+      "step": 171
+    },
+    {
+      "Batch Sum": 164.240966796875,
+      "accuracy": 0.75,
+      "epoch": 0.4275,
+      "step": 171
+    },
+    {
+      "Batch Sum": 187.87646484375,
+      "accuracy": 0.84375,
+      "epoch": 0.4275,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 12.420621871948242,
+      "learning_rate": 3e-06,
+      "loss": 0.3898,
+      "step": 172
+    },
+    {
+      "Batch Sum": 168.580810546875,
+      "accuracy": 0.796875,
+      "epoch": 0.43,
+      "step": 172
+    },
+    {
+      "Batch Sum": 183.23199462890625,
+      "accuracy": 0.84375,
+      "epoch": 0.43,
+      "step": 172
+    },
+    {
+      "epoch": 0.4325,
+      "grad_norm": 11.917014122009277,
+      "learning_rate": 2.986842105263158e-06,
+      "loss": 0.3652,
+      "step": 173
+    },
+    {
+      "Batch Sum": 180.752685546875,
+      "accuracy": 0.8125,
+      "epoch": 0.4325,
+      "step": 173
+    },
+    {
+      "Batch Sum": 174.8634033203125,
+      "accuracy": 0.78125,
+      "epoch": 0.4325,
+      "step": 173
+    },
+    {
+      "epoch": 0.435,
+      "grad_norm": 13.711872100830078,
+      "learning_rate": 2.973684210526316e-06,
+      "loss": 0.4049,
+      "step": 174
+    },
+    {
+      "Batch Sum": 187.95513916015625,
+      "accuracy": 0.859375,
+      "epoch": 0.435,
+      "step": 174
+    },
+    {
+      "Batch Sum": 175.5262451171875,
+      "accuracy": 0.90625,
+      "epoch": 0.435,
+      "step": 174
+    },
+    {
+      "epoch": 0.4375,
+      "grad_norm": 13.002115249633789,
+      "learning_rate": 2.960526315789474e-06,
+      "loss": 0.3187,
+      "step": 175
+    },
+    {
+      "Batch Sum": 193.835693359375,
+      "accuracy": 0.890625,
+      "epoch": 0.4375,
+      "step": 175
+    },
+    {
+      "Batch Sum": 178.1373291015625,
+      "accuracy": 0.875,
+      "epoch": 0.4375,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 10.474250793457031,
+      "learning_rate": 2.9473684210526317e-06,
+      "loss": 0.2761,
+      "step": 176
+    },
+    {
+      "Batch Sum": 204.98779296875,
+      "accuracy": 0.78125,
+      "epoch": 0.44,
+      "step": 176
+    },
+    {
+      "Batch Sum": 176.36172485351562,
+      "accuracy": 0.84375,
+      "epoch": 0.44,
+      "step": 176
+    },
+    {
+      "epoch": 0.4425,
+      "grad_norm": 13.780770301818848,
+      "learning_rate": 2.93421052631579e-06,
+      "loss": 0.4051,
+      "step": 177
+    },
+    {
+      "Batch Sum": 182.67578125,
+      "accuracy": 0.890625,
+      "epoch": 0.4425,
+      "step": 177
+    },
+    {
+      "Batch Sum": 186.214111328125,
+      "accuracy": 0.859375,
+      "epoch": 0.4425,
+      "step": 177
+    },
+    {
+      "epoch": 0.445,
+      "grad_norm": 11.39830207824707,
+      "learning_rate": 2.921052631578948e-06,
+      "loss": 0.3473,
+      "step": 178
+    },
+    {
+      "Batch Sum": 177.402587890625,
+      "accuracy": 0.84375,
+      "epoch": 0.445,
+      "step": 178
+    },
+    {
+      "Batch Sum": 189.29144287109375,
+      "accuracy": 0.828125,
+      "epoch": 0.445,
+      "step": 178
+    },
+    {
+      "epoch": 0.4475,
+      "grad_norm": 13.348224639892578,
+      "learning_rate": 2.907894736842106e-06,
+      "loss": 0.3464,
+      "step": 179
+    },
+    {
+      "Batch Sum": 184.62939453125,
+      "accuracy": 0.859375,
+      "epoch": 0.4475,
+      "step": 179
+    },
+    {
+      "Batch Sum": 171.792236328125,
+      "accuracy": 0.78125,
+      "epoch": 0.4475,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 13.45236587524414,
+      "learning_rate": 2.8947368421052634e-06,
+      "loss": 0.3707,
+      "step": 180
+    },
+    {
+      "Batch Sum": 183.537353515625,
+      "accuracy": 0.828125,
+      "epoch": 0.45,
+      "step": 180
+    },
+    {
+      "Batch Sum": 184.44140625,
+      "accuracy": 0.875,
+      "epoch": 0.45,
+      "step": 180
+    },
+    {
+      "epoch": 0.4525,
+      "grad_norm": 11.033170700073242,
+      "learning_rate": 2.8815789473684213e-06,
+      "loss": 0.3141,
+      "step": 181
+    },
+    {
+      "Batch Sum": 157.82540893554688,
+      "accuracy": 0.796875,
+      "epoch": 0.4525,
+      "step": 181
+    },
+    {
+      "Batch Sum": 178.438720703125,
+      "accuracy": 0.796875,
+      "epoch": 0.4525,
+      "step": 181
+    },
+    {
+      "epoch": 0.455,
+      "grad_norm": 13.729015350341797,
+      "learning_rate": 2.868421052631579e-06,
+      "loss": 0.4089,
+      "step": 182
+    },
+    {
+      "Batch Sum": 178.9556884765625,
+      "accuracy": 0.734375,
+      "epoch": 0.455,
+      "step": 182
+    },
+    {
+      "Batch Sum": 181.88690185546875,
+      "accuracy": 0.84375,
+      "epoch": 0.455,
+      "step": 182
+    },
+    {
+      "epoch": 0.4575,
+      "grad_norm": 16.668292999267578,
+      "learning_rate": 2.855263157894737e-06,
+      "loss": 0.5041,
+      "step": 183
+    },
+    {
+      "Batch Sum": 170.711181640625,
+      "accuracy": 0.796875,
+      "epoch": 0.4575,
+      "step": 183
+    },
+    {
+      "Batch Sum": 169.305908203125,
+      "accuracy": 0.796875,
+      "epoch": 0.4575,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 11.935322761535645,
+      "learning_rate": 2.842105263157895e-06,
+      "loss": 0.4036,
+      "step": 184
+    },
+    {
+      "Batch Sum": 159.673828125,
+      "accuracy": 0.796875,
+      "epoch": 0.46,
+      "step": 184
+    },
+    {
+      "Batch Sum": 148.835693359375,
+      "accuracy": 0.828125,
+      "epoch": 0.46,
+      "step": 184
+    },
+    {
+      "epoch": 0.4625,
+      "grad_norm": 12.534523010253906,
+      "learning_rate": 2.828947368421053e-06,
+      "loss": 0.3995,
+      "step": 185
+    },
+    {
+      "Batch Sum": 137.3509521484375,
+      "accuracy": 0.859375,
+      "epoch": 0.4625,
+      "step": 185
+    },
+    {
+      "Batch Sum": 137.57501220703125,
+      "accuracy": 0.875,
+      "epoch": 0.4625,
+      "step": 185
+    },
+    {
+      "epoch": 0.465,
+      "grad_norm": 10.489812850952148,
+      "learning_rate": 2.815789473684211e-06,
+      "loss": 0.3355,
+      "step": 186
+    },
+    {
+      "Batch Sum": 149.32647705078125,
+      "accuracy": 0.84375,
+      "epoch": 0.465,
+      "step": 186
+    },
+    {
+      "Batch Sum": 137.6878662109375,
+      "accuracy": 0.890625,
+      "epoch": 0.465,
+      "step": 186
+    },
+    {
+      "epoch": 0.4675,
+      "grad_norm": 10.799548149108887,
+      "learning_rate": 2.8026315789473683e-06,
+      "loss": 0.3154,
+      "step": 187
+    },
+    {
+      "Batch Sum": 140.84820556640625,
+      "accuracy": 0.84375,
+      "epoch": 0.4675,
+      "step": 187
+    },
+    {
+      "Batch Sum": 137.59814453125,
+      "accuracy": 0.796875,
+      "epoch": 0.4675,
+      "step": 187
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 10.771398544311523,
+      "learning_rate": 2.789473684210526e-06,
+      "loss": 0.3794,
+      "step": 188
+    },
+    {
+      "Batch Sum": 120.0439453125,
+      "accuracy": 0.828125,
+      "epoch": 0.47,
+      "step": 188
+    },
+    {
+      "Batch Sum": 132.53411865234375,
+      "accuracy": 0.890625,
+      "epoch": 0.47,
+      "step": 188
+    },
+    {
+      "epoch": 0.4725,
+      "grad_norm": 8.793214797973633,
+      "learning_rate": 2.776315789473684e-06,
+      "loss": 0.3329,
+      "step": 189
+    },
+    {
+      "Batch Sum": 148.12432861328125,
+      "accuracy": 0.796875,
+      "epoch": 0.4725,
+      "step": 189
+    },
+    {
+      "Batch Sum": 123.746826171875,
+      "accuracy": 0.765625,
+      "epoch": 0.4725,
+      "step": 189
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 10.795166969299316,
+      "learning_rate": 2.7631578947368424e-06,
+      "loss": 0.3926,
+      "step": 190
+    },
+    {
+      "Batch Sum": 144.51519775390625,
+      "accuracy": 0.796875,
+      "epoch": 0.475,
+      "step": 190
+    },
+    {
+      "Batch Sum": 156.36366271972656,
+      "accuracy": 0.84375,
+      "epoch": 0.475,
+      "step": 190
+    },
+    {
+      "epoch": 0.4775,
+      "grad_norm": 11.242524147033691,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.4088,
+      "step": 191
+    },
+    {
+      "Batch Sum": 132.588134765625,
+      "accuracy": 0.734375,
+      "epoch": 0.4775,
+      "step": 191
+    },
+    {
+      "Batch Sum": 132.279296875,
+      "accuracy": 0.765625,
+      "epoch": 0.4775,
+      "step": 191
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 11.10943603515625,
+      "learning_rate": 2.7368421052631583e-06,
+      "loss": 0.4502,
+      "step": 192
+    },
+    {
+      "Batch Sum": 127.26214599609375,
+      "accuracy": 0.765625,
+      "epoch": 0.48,
+      "step": 192
+    },
+    {
+      "Batch Sum": 120.28961181640625,
+      "accuracy": 0.734375,
+      "epoch": 0.48,
+      "step": 192
+    },
+    {
+      "epoch": 0.4825,
+      "grad_norm": 10.466278076171875,
+      "learning_rate": 2.723684210526316e-06,
+      "loss": 0.4388,
+      "step": 193
+    },
+    {
+      "Batch Sum": 137.3543701171875,
+      "accuracy": 0.875,
+      "epoch": 0.4825,
+      "step": 193
+    },
+    {
+      "Batch Sum": 126.865234375,
+      "accuracy": 0.875,
+      "epoch": 0.4825,
+      "step": 193
+    },
+    {
+      "epoch": 0.485,
+      "grad_norm": 9.617724418640137,
+      "learning_rate": 2.710526315789474e-06,
+      "loss": 0.3097,
+      "step": 194
+    },
+    {
+      "Batch Sum": 141.0351104736328,
+      "accuracy": 0.859375,
+      "epoch": 0.485,
+      "step": 194
+    },
+    {
+      "Batch Sum": 115.21342468261719,
+      "accuracy": 0.765625,
+      "epoch": 0.485,
+      "step": 194
+    },
+    {
+      "epoch": 0.4875,
+      "grad_norm": 9.829240798950195,
+      "learning_rate": 2.697368421052632e-06,
+      "loss": 0.4003,
+      "step": 195
+    },
+    {
+      "Batch Sum": 140.189697265625,
+      "accuracy": 0.875,
+      "epoch": 0.4875,
+      "step": 195
+    },
+    {
+      "Batch Sum": 147.9466552734375,
+      "accuracy": 0.84375,
+      "epoch": 0.4875,
+      "step": 195
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 9.37118911743164,
+      "learning_rate": 2.68421052631579e-06,
+      "loss": 0.3677,
+      "step": 196
+    },
+    {
+      "Batch Sum": 148.1060791015625,
+      "accuracy": 0.71875,
+      "epoch": 0.49,
+      "step": 196
+    },
+    {
+      "Batch Sum": 131.451171875,
+      "accuracy": 0.84375,
+      "epoch": 0.49,
+      "step": 196
+    },
+    {
+      "epoch": 0.4925,
+      "grad_norm": 11.06047534942627,
+      "learning_rate": 2.6710526315789474e-06,
+      "loss": 0.4126,
+      "step": 197
+    },
+    {
+      "Batch Sum": 144.2012939453125,
+      "accuracy": 0.828125,
+      "epoch": 0.4925,
+      "step": 197
+    },
+    {
+      "Batch Sum": 141.30419921875,
+      "accuracy": 0.8125,
+      "epoch": 0.4925,
+      "step": 197
+    },
+    {
+      "epoch": 0.495,
+      "grad_norm": 9.70101261138916,
+      "learning_rate": 2.6578947368421053e-06,
+      "loss": 0.3397,
+      "step": 198
+    },
+    {
+      "Batch Sum": 149.09429931640625,
+      "accuracy": 0.828125,
+      "epoch": 0.495,
+      "step": 198
+    },
+    {
+      "Batch Sum": 141.2196044921875,
+      "accuracy": 0.828125,
+      "epoch": 0.495,
+      "step": 198
+    },
+    {
+      "epoch": 0.4975,
+      "grad_norm": 9.994836807250977,
+      "learning_rate": 2.644736842105263e-06,
+      "loss": 0.3922,
+      "step": 199
+    },
+    {
+      "Batch Sum": 150.16015625,
+      "accuracy": 0.78125,
+      "epoch": 0.4975,
+      "step": 199
+    },
+    {
+      "Batch Sum": 149.1392822265625,
+      "accuracy": 0.75,
+      "epoch": 0.4975,
+      "step": 199
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 10.291372299194336,
+      "learning_rate": 2.631578947368421e-06,
+      "loss": 0.4164,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d77beb5f705beb14f5ec1440aa188d529fdd21781b719b9045947924bf26324
+size 5752

checkpoint-300/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-300/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "tlrm/Q25-1.5B-UC",
+  "architectures": [
+    "Qwen2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-300/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6352710bbb2f3b19df172533fd691d1ffe0d0a8376c76db082de847479927ae
+size 4996670464

checkpoint-300/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9062095e5c38312cd436bfde4e09bba8ae26c176eca1c9bf0fe9783aec20dfce
+size 1178231192

checkpoint-300/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 6174863360
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "score.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-300/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-300/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-300/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n   {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d77beb5f705beb14f5ec1440aa188d529fdd21781b719b9045947924bf26324
+size 5752

checkpoint-400/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-400/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "tlrm/Q25-1.5B-UC",
+  "architectures": [
+    "Qwen2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-400/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67a196bfbb4fb9c37998386bdbcf89a267ef0921c38b74e8b169b2a5c7705f21
+size 4996670464

checkpoint-400/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:982c22858f6648312167ddba680bebafda0c7582292a7e4180360348df705d48
+size 1178231192

checkpoint-400/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 6174863360
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "score.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-400/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-400/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-400/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n   {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d77beb5f705beb14f5ec1440aa188d529fdd21781b719b9045947924bf26324
+size 5752